Crevio
An AI agent that runs your online business: products, orders, customers, email, and sites.
我该使用它吗
质量与安全性
A
基于对工具定义和协议合规性的自动分析。
上下文开销
~8,350token 数（工具定义）
~4.7 KB典型响应大小
对注意力有显著影响（占 128k 上下文窗口的 6.52%）
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"crevio": {
"url": "https://mcp.crevio.co/mcp"
}
}
}远程端点
https://mcp.crevio.co/mcpstreamable-http它能做什么
工具清单
工具（18）
🟢 只读🟡 写入🔴 删除⚪ 未知
🟢whoami
Identify the account, user, and credential behind this connection, with plan, credit balance, rate limits, and the tools available. Only needed to troubleshoot the connection or check credits and limits — other tools already act on this account.
输入模式
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}输出模式
{
"type": "object",
"properties": {
"object": {
"type": "string",
"const": "whoami"
},
"account": {
"type": "object",
"description": "The account every tool call is scoped to.",
"properties": {
"id": {
"type": "string"
},
"name": {
"type": "string"
},
"slug": {
"type": [
"string",
"null"
]
}
},
"required": [
"id",
"name"
]
},
"user": {
"type": [
"object",
"null"
],
"properties": {
"id": {
"type": "string"
},
"email": {
"type": "string"
},
"name": {
"type": [
"string",
"null"
]
}
},
"required": [
"id",
"email"
]
},
"credential": {
"type": "object",
"description": "How this connection authenticated.",
"properties": {
"type": {
"type": "string",
"enum": [
"api_key",
"oauth"
]
},
"id": {
"type": "string"
},
"name": {
"type": [
"string",
"null"
]
},
"expires_at": {
"type": [
"string",
"null"
],
"format": "date-time"
}
},
"required": [
"type"
]
},
"plan": {
"type": "string"
},
"credits": {
"type": "number"
},
"rate_limit": {
"type": "object",
"description": "The API rate limit this credential is subject to.",
"properties": {
"limit": {
"type": "integer"
},
"window_seconds": {
"type": "integer"
}
},
"required": [
"limit",
"window_seconds"
]
},
"limits": {
"type": "object",
"description": "Bounds the delegation tools enforce.",
"properties": {
"ask_timeout_default_seconds": {
"type": "integer"
},
"ask_timeout_max_seconds": {
"type": "integer",
"description": "Longer when this connection accepts a streamed reply."
},
"message_max_chars": {
"type": "integer"
}
},
"required": [
"ask_timeout_default_seconds",
"ask_timeout_max_seconds",
"message_max_chars"
]
},
"tools": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"object",
"account",
"credential",
"plan",
"credits",
"tools"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"description": "The account, user, and credential behind this connection, with the limits that apply to it."
}🟢list_integrations
List what a script can call: the Crevio API (crevioApi), Crevio's own tools (platform), and every integration you can use, each as a namespace under `tools`, plus the account's other connected apps and their status. Then list a namespace's functions with list_integration_tools.
输入模式
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}输出模式
{
"type": "object",
"properties": {
"object": {
"type": "string",
"const": "list"
},
"data": {
"type": "array",
"items": {
"type": "object",
"properties": {
"namespace": {
"type": "string",
"description": "The module a script calls it through: tools.<namespace>.<function>."
},
"kind": {
"type": "string",
"enum": [
"native",
"crevio_api",
"connection",
"public"
]
},
"label": {
"type": [
"string",
"null"
],
"description": "Which connected account, when the app is connected more than once or personally."
},
"tool_count": {
"type": "integer"
}
},
"required": [
"namespace",
"kind",
"tool_count"
]
}
},
"other_connections": {
"type": "array",
"description": "Connected apps without a namespace of their own: expired ones need reconnecting in Crevio, social accounts are reached through crevioApi, and the rest serve Crevio itself (Slack for chat, GitHub for sites).",
"items": {
"type": "object",
"properties": {
"app": {
"type": "string"
},
"label": {
"type": [
"string",
"null"
]
},
"status": {
"type": "string"
}
},
"required": [
"app",
"status"
]
}
}
},
"required": [
"object",
"data",
"other_connections"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢list_integration_tools(namespace, search, limit, offset)
List one namespace's functions — the name a script calls, its parameters, whether it only reads, whether it needs approval, and a snippet run_script accepts. crevioApi has hundreds of operations: narrow it with `search`.
输入模式
{
"type": "object",
"properties": {
"namespace": {
"type": "string",
"description": "A namespace from list_integrations, e.g. crevioApi or pdGmail."
},
"search": {
"type": "string",
"description": "Only functions whose name or description matches every word."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"description": "Default 10."
},
"offset": {
"type": "integer",
"minimum": 0,
"description": "Skip this many matches — the count already seen."
}
},
"required": [
"namespace"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}输出模式
{
"type": "object",
"properties": {
"object": {
"type": "string",
"const": "list"
},
"data": {
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "What a script calls: tools.<namespace>.<function>."
},
"description": {
"type": [
"string",
"null"
]
},
"parameters": {
"type": "string",
"description": "The argument object, as a TypeScript type."
},
"returns": {
"type": "string",
"description": "What a read resolves to, as a TypeScript type; objects past two levels show as Record<string, unknown>."
},
"read_only": {
"type": "boolean"
},
"requires_approval": {
"type": "boolean",
"description": "A script cannot ask for approval, so calling it fails unless the account sets it to run automatically."
},
"disabled": {
"type": "boolean"
},
"snippet": {
"type": "string",
"description": "A script run_script accepts as-is once the placeholders are filled."
}
},
"required": [
"name",
"parameters",
"read_only",
"requires_approval",
"disabled",
"snippet"
]
}
},
"has_more": {
"type": "boolean"
}
},
"required": [
"object",
"data",
"has_more"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🔴run_script(code, timeout_seconds, wait_seconds, idempotency_key)
Run JavaScript on the account's computer with bun — no agent turn — and wait for its result. `tools.<namespace>.<function>(args)` calls anything list_integration_tools shows (every call returns its result and throws on failure; top-level await works), and the script's last expression is its result. Chain calls and transform data in one run, e.g. `const { data } = await tools.crevioApi.listOrders({ status: "succeeded" }); data.length`. Runs as you, and only for account admins. If the wait ends first the reply has wait_timed_out: true and the run id: continue with wait_for_script_run — calling run_script again runs it twice unless you reuse the idempotency_key. Run ids do not expire, and only the user who started a run can read it. At most 4 runs in flight per user.
输入模式
{
"type": "object",
"properties": {
"code": {
"type": "string",
"maxLength": 100000,
"description": "The JavaScript to run."
},
"timeout_seconds": {
"type": "integer",
"minimum": 1,
"maximum": 600,
"description": "How long the script may run (default 300)."
},
"wait_seconds": {
"type": "integer",
"minimum": 0,
"maximum": 300,
"description": "How long to wait for the script to finish before returning. Defaults to, and is capped at, 300 s when your client accepts a streamed reply (text/event-stream), 90 s otherwise. The script keeps going when the wait ends first."
},
"idempotency_key": {
"type": "string",
"maxLength": 255,
"description": "Always pass one, unique to this request. Retrying with the same key within an hour returns the run the first call started instead of doing the job twice."
}
},
"required": [
"code"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}输出模式
{
"type": "object",
"properties": {
"object": {
"type": "string",
"const": "script_run"
},
"id": {
"type": "string"
},
"status": {
"type": "string",
"enum": [
"queued",
"in_progress",
"completed",
"failed",
"cancelled",
"timed_out"
]
},
"result": {
"description": "The script's last expression, as JSON."
},
"output": {
"type": [
"string",
"null"
],
"description": "What the script printed (the last 64,000 characters)."
},
"error": {
"type": [
"string",
"null"
]
},
"calls": {
"type": "array",
"description": "Every tool call the script made, in order.",
"items": {
"type": "object",
"properties": {
"role": {
"type": "string"
},
"status": {
"type": "integer"
},
"read_only": {
"type": "boolean"
},
"error_code": {
"type": "string"
}
},
"required": [
"role"
]
}
},
"timeout_seconds": {
"type": "integer"
},
"created_at": {
"type": "string",
"format": "date-time"
},
"started_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"completed_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"reused": {
"type": "boolean"
},
"wait_timed_out": {
"type": "boolean",
"description": "The wait ended first. The work is still running: follow it with the tool next_step names."
},
"next_step": {
"type": "string"
}
},
"required": [
"object",
"id",
"status",
"calls",
"timeout_seconds",
"created_at"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"description": "One script run on the account's computer."
}🟢wait_for_script_run(run_id, wait_seconds)
Wait for a script run to finish and return its result. If it is still running when the wait ends, the reply has wait_timed_out: true — call again.
输入模式
{
"type": "object",
"properties": {
"run_id": {
"type": "string",
"description": "A script run id (srun_...)."
},
"wait_seconds": {
"type": "integer",
"minimum": 0,
"maximum": 300,
"description": "How long to wait for the script to finish before returning. Defaults to, and is capped at, 300 s when your client accepts a streamed reply (text/event-stream), 90 s otherwise. The script keeps going when the wait ends first."
}
},
"required": [
"run_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}输出模式
{
"type": "object",
"properties": {
"object": {
"type": "string",
"const": "script_run"
},
"id": {
"type": "string"
},
"status": {
"type": "string",
"enum": [
"queued",
"in_progress",
"completed",
"failed",
"cancelled",
"timed_out"
]
},
"result": {
"description": "The script's last expression, as JSON."
},
"output": {
"type": [
"string",
"null"
],
"description": "What the script printed (the last 64,000 characters)."
},
"error": {
"type": [
"string",
"null"
]
},
"calls": {
"type": "array",
"description": "Every tool call the script made, in order.",
"items": {
"type": "object",
"properties": {
"role": {
"type": "string"
},
"status": {
"type": "integer"
},
"read_only": {
"type": "boolean"
},
"error_code": {
"type": "string"
}
},
"required": [
"role"
]
}
},
"timeout_seconds": {
"type": "integer"
},
"created_at": {
"type": "string",
"format": "date-time"
},
"started_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"completed_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"reused": {
"type": "boolean"
},
"wait_timed_out": {
"type": "boolean",
"description": "The wait ended first. The work is still running: follow it with the tool next_step names."
},
"next_step": {
"type": "string"
}
},
"required": [
"object",
"id",
"status",
"calls",
"timeout_seconds",
"created_at"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"description": "One script run on the account's computer."
}🟢get_script_run(run_id)
Read a script run's status, and its result once it has finished.
输入模式
{
"type": "object",
"properties": {
"run_id": {
"type": "string",
"description": "A script run id (srun_...)."
}
},
"required": [
"run_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}输出模式
{
"type": "object",
"properties": {
"object": {
"type": "string",
"const": "script_run"
},
"id": {
"type": "string"
},
"status": {
"type": "string",
"enum": [
"queued",
"in_progress",
"completed",
"failed",
"cancelled",
"timed_out"
]
},
"result": {
"description": "The script's last expression, as JSON."
},
"output": {
"type": [
"string",
"null"
],
"description": "What the script printed (the last 64,000 characters)."
},
"error": {
"type": [
"string",
"null"
]
},
"calls": {
"type": "array",
"description": "Every tool call the script made, in order.",
"items": {
"type": "object",
"properties": {
"role": {
"type": "string"
},
"status": {
"type": "integer"
},
"read_only": {
"type": "boolean"
},
"error_code": {
"type": "string"
}
},
"required": [
"role"
]
}
},
"timeout_seconds": {
"type": "integer"
},
"created_at": {
"type": "string",
"format": "date-time"
},
"started_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"completed_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"reused": {
"type": "boolean"
},
"wait_timed_out": {
"type": "boolean",
"description": "The wait ended first. The work is still running: follow it with the tool next_step names."
},
"next_step": {
"type": "string"
}
},
"required": [
"object",
"id",
"status",
"calls",
"timeout_seconds",
"created_at"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"description": "One script run on the account's computer."
}🔴cancel_script_run(run_id)
Cancel a script run that has not started yet. A running script runs to its end or its timeout.
输入模式
{
"type": "object",
"properties": {
"run_id": {
"type": "string",
"description": "A script run id (srun_...)."
}
},
"required": [
"run_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}输出模式
{
"type": "object",
"properties": {
"object": {
"type": "string",
"const": "script_run"
},
"id": {
"type": "string"
},
"status": {
"type": "string",
"enum": [
"queued",
"in_progress",
"completed",
"failed",
"cancelled",
"timed_out"
]
},
"result": {
"description": "The script's last expression, as JSON."
},
"output": {
"type": [
"string",
"null"
],
"description": "What the script printed (the last 64,000 characters)."
},
"error": {
"type": [
"string",
"null"
]
},
"calls": {
"type": "array",
"description": "Every tool call the script made, in order.",
"items": {
"type": "object",
"properties": {
"role": {
"type": "string"
},
"status": {
"type": "integer"
},
"read_only": {
"type": "boolean"
},
"error_code": {
"type": "string"
}
},
"required": [
"role"
]
}
},
"timeout_seconds": {
"type": "integer"
},
"created_at": {
"type": "string",
"format": "date-time"
},
"started_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"completed_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"reused": {
"type": "boolean"
},
"wait_timed_out": {
"type": "boolean",
"description": "The wait ended first. The work is still running: follow it with the tool next_step names."
},
"next_step": {
"type": "string"
}
},
"required": [
"object",
"id",
"status",
"calls",
"timeout_seconds",
"created_at"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"description": "One script run on the account's computer."
}🔴ask_crevio(message, timeout_seconds, approval_mode, speed, idempotency_key)
Delegate a job to the Crevio agent and wait for the result. The agent works your account through the Crevio API and every connected integration (products, customers, orders, email, socials, sites, research) and replies in `result`. Each job is a full agent run that takes from half a minute to several minutes, so use it for work that needs judgement or writing. If the run is still going when the wait ends, the reply has wait_timed_out: true — then call wait_for_run with its id and never call ask_crevio again, which would do the job twice. Run ids do not expire, and only the user who started a run can read it.
输入模式
{
"type": "object",
"properties": {
"message": {
"type": "string",
"maxLength": 10000,
"description": "What you want done, in natural language, with all the context needed — the agent does not see your conversation."
},
"timeout_seconds": {
"type": "integer",
"minimum": 0,
"maximum": 300,
"description": "How long to wait for the run to finish before returning. Defaults to, and is capped at, 300 s when your client accepts a streamed reply (text/event-stream), 90 s otherwise. The run keeps going when the wait ends first."
},
"approval_mode": {
"type": "string",
"enum": [
"autonomous",
"supervised",
"read_only"
],
"description": "autonomous (default) acts without review; supervised pauses in needs_input for your approval before each gated write (pending_approval_ids) and otherwise finishes with its proposal; read_only forbids writes."
},
"speed": {
"type": "string",
"enum": [
"faster",
"smarter"
],
"description": "faster thinks less, for simple jobs where latency matters more than depth; smarter (default) thinks it through."
},
"idempotency_key": {
"type": "string",
"maxLength": 255,
"description": "Always pass one, unique to this request. Retrying with the same key within an hour returns the run the first call started instead of doing the job twice."
}
},
"required": [
"message"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}输出模式
{
"type": "object",
"properties": {
"object": {
"type": "string",
"const": "task_run"
},
"id": {
"type": "string"
},
"task_id": {
"type": "string"
},
"task_name": {
"type": [
"string",
"null"
]
},
"chat_id": {
"type": [
"string",
"null"
]
},
"status": {
"type": "string",
"enum": [
"pending",
"running",
"completed",
"failed",
"needs_input",
"timed_out",
"unknown",
"skipped"
]
},
"summary": {
"type": [
"string",
"null"
]
},
"error_message": {
"type": [
"string",
"null"
]
},
"pending_approval_ids": {
"type": "array",
"items": {
"type": "string"
}
},
"reused": {
"type": "boolean"
},
"wait_timed_out": {
"type": "boolean",
"description": "The wait ended first. The work is still running: follow it with the tool next_step names."
},
"next_step": {
"type": "string"
},
"credits_consumed": {
"type": "integer"
},
"started_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"completed_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"created_at": {
"type": "string",
"format": "date-time"
},
"result": {
"type": [
"string",
"null"
]
}
},
"required": [
"object",
"id",
"task_id",
"status",
"created_at"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"description": "A task run — one delegated job and what is known about its state."
}🔴start_chat(message, approval_mode, speed, idempotency_key)
Open a chat with the Crevio agent and queue a run, without waiting. Returns the run immediately — its `chat_id` is the conversation to continue with send_message. Follow the run with wait_for_run or get_run.
输入模式
{
"type": "object",
"properties": {
"message": {
"type": "string",
"maxLength": 10000,
"description": "What you want done, in natural language, with all the context needed — the agent does not see your conversation."
},
"approval_mode": {
"type": "string",
"enum": [
"autonomous",
"supervised",
"read_only"
],
"description": "autonomous (default) acts without review; supervised pauses in needs_input for your approval before each gated write (pending_approval_ids) and otherwise finishes with its proposal; read_only forbids writes."
},
"speed": {
"type": "string",
"enum": [
"faster",
"smarter"
],
"description": "faster thinks less, for simple jobs where latency matters more than depth; smarter (default) thinks it through."
},
"idempotency_key": {
"type": "string",
"maxLength": 255,
"description": "Always pass one, unique to this request. Retrying with the same key within an hour returns the run the first call started instead of doing the job twice."
}
},
"required": [
"message"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}输出模式
{
"type": "object",
"properties": {
"object": {
"type": "string",
"const": "task_run"
},
"id": {
"type": "string"
},
"task_id": {
"type": "string"
},
"task_name": {
"type": [
"string",
"null"
]
},
"chat_id": {
"type": [
"string",
"null"
]
},
"status": {
"type": "string",
"enum": [
"pending",
"running",
"completed",
"failed",
"needs_input",
"timed_out",
"unknown",
"skipped"
]
},
"summary": {
"type": [
"string",
"null"
]
},
"error_message": {
"type": [
"string",
"null"
]
},
"pending_approval_ids": {
"type": "array",
"items": {
"type": "string"
}
},
"reused": {
"type": "boolean"
},
"wait_timed_out": {
"type": "boolean",
"description": "The wait ended first. The work is still running: follow it with the tool next_step names."
},
"next_step": {
"type": "string"
},
"credits_consumed": {
"type": "integer"
},
"started_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"completed_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"created_at": {
"type": "string",
"format": "date-time"
},
"result": {
"type": [
"string",
"null"
]
}
},
"required": [
"object",
"id",
"task_id",
"status",
"created_at"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"description": "A task run — one delegated job and what is known about its state."
}🟢list_chats(search, limit, starting_after, ending_before)
List the account's chats, newest first.
输入模式
{
"type": "object",
"properties": {
"search": {
"type": "string",
"description": "Only chats whose title matches."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"description": "Default 20."
},
"starting_after": {
"type": "string",
"description": "Return the page after this id — the last id from the previous page."
},
"ending_before": {
"type": "string",
"description": "Return the page before this id — the first id from the previous page."
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}输出模式
{
"type": "object",
"properties": {
"object": {
"type": "string",
"const": "list"
},
"data": {
"type": "array",
"items": {
"type": "object",
"description": "A chat — one conversation with the agent, across however many runs it took.",
"properties": {
"object": {
"type": "string",
"const": "chat"
},
"id": {
"type": "string"
},
"title": {
"type": [
"string",
"null"
]
},
"context_type": {
"type": [
"string",
"null"
],
"enum": [
"general",
"ai_builder",
"customer_support",
"onboarding",
null
]
},
"latest_run_id": {
"type": [
"string",
"null"
]
},
"created_at": {
"type": "string",
"format": "date-time"
},
"updated_at": {
"type": "string",
"format": "date-time"
}
},
"required": [
"object",
"id",
"created_at"
]
}
},
"has_more": {
"type": "boolean"
}
},
"required": [
"object",
"data",
"has_more"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"description": "A page of chats, newest first."
}🟢get_chat(chat_id)
Get a chat's title, kind, and latest run.
输入模式
{
"type": "object",
"properties": {
"chat_id": {
"type": "string",
"description": "A chat id (aichat_...). A run id works too — it resolves to that run's chat."
}
},
"required": [
"chat_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}输出模式
{
"type": "object",
"properties": {
"object": {
"type": "string",
"const": "chat"
},
"id": {
"type": "string"
},
"title": {
"type": [
"string",
"null"
]
},
"context_type": {
"type": [
"string",
"null"
],
"enum": [
"general",
"ai_builder",
"customer_support",
"onboarding",
null
]
},
"latest_run_id": {
"type": [
"string",
"null"
]
},
"created_at": {
"type": "string",
"format": "date-time"
},
"updated_at": {
"type": "string",
"format": "date-time"
}
},
"required": [
"object",
"id",
"created_at"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"description": "A chat — one conversation with the agent, across however many runs it took."
}🔴send_message(chat_id, message, timeout_seconds)
Continue a chat with follow-up instructions or answers — the agent keeps its context. Resumes a run waiting in needs_input, or queues a new run when the last one finished. Returns run_busy while a run is still in progress. Optionally waits for the reply.
输入模式
{
"type": "object",
"properties": {
"chat_id": {
"type": "string",
"description": "A chat id (aichat_...). A run id works too — it resolves to that run's chat."
},
"message": {
"type": "string",
"maxLength": 10000,
"description": "The follow-up to send into the conversation."
},
"timeout_seconds": {
"type": "integer",
"minimum": 0,
"maximum": 300,
"description": "Seconds to wait for the reply before returning (default 0: return the new run immediately). Capped like ask_crevio's wait."
}
},
"required": [
"chat_id",
"message"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}输出模式
{
"type": "object",
"properties": {
"object": {
"type": "string",
"const": "task_run"
},
"id": {
"type": "string"
},
"task_id": {
"type": "string"
},
"task_name": {
"type": [
"string",
"null"
]
},
"chat_id": {
"type": [
"string",
"null"
]
},
"status": {
"type": "string",
"enum": [
"pending",
"running",
"completed",
"failed",
"needs_input",
"timed_out",
"unknown",
"skipped"
]
},
"summary": {
"type": [
"string",
"null"
]
},
"error_message": {
"type": [
"string",
"null"
]
},
"pending_approval_ids": {
"type": "array",
"items": {
"type": "string"
}
},
"reused": {
"type": "boolean"
},
"wait_timed_out": {
"type": "boolean",
"description": "The wait ended first. The work is still running: follow it with the tool next_step names."
},
"next_step": {
"type": "string"
},
"credits_consumed": {
"type": "integer"
},
"started_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"completed_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"created_at": {
"type": "string",
"format": "date-time"
},
"result": {
"type": [
"string",
"null"
]
}
},
"required": [
"object",
"id",
"task_id",
"status",
"created_at"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"description": "A task run — one delegated job and what is known about its state."
}🟢list_messages(chat_id, limit, ending_before)
Read a chat's messages, oldest first. Returns the most recent `limit` messages; page back through older ones with starting_after.
输入模式
{
"type": "object",
"properties": {
"chat_id": {
"type": "string",
"description": "A chat id (aichat_...). A run id works too — it resolves to that run's chat."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 200,
"description": "Default 50."
},
"ending_before": {
"type": "string",
"description": "Return the messages older than this id — the first id of the previous page. Paging walks backwards through history, since the default page is the tail."
}
},
"required": [
"chat_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}输出模式
{
"type": "object",
"properties": {
"object": {
"type": "string",
"const": "list"
},
"data": {
"type": "array",
"items": {
"type": "object",
"description": "One message in a run's conversation.",
"properties": {
"id": {
"type": "string"
},
"role": {
"type": "string",
"enum": [
"user",
"assistant"
]
},
"content": {
"type": "string"
},
"created_at": {
"type": "string",
"format": "date-time"
}
},
"required": [
"id",
"role",
"content",
"created_at"
]
}
},
"has_more": {
"type": "boolean"
}
},
"required": [
"object",
"data",
"has_more"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"description": "A page of conversation messages, oldest first."
}🟢wait_for_run(run_id, timeout_seconds)
Wait for a run to settle (completed, failed, or needs_input) and return it with the agent's final reply. If it is still running when the wait ends, the reply has wait_timed_out: true — call wait_for_run again.
输入模式
{
"type": "object",
"properties": {
"run_id": {
"type": "string",
"description": "A run id (trun_...)."
},
"timeout_seconds": {
"type": "integer",
"minimum": 0,
"maximum": 300,
"description": "How long to wait for the run to finish before returning. Defaults to, and is capped at, 300 s when your client accepts a streamed reply (text/event-stream), 90 s otherwise. The run keeps going when the wait ends first."
}
},
"required": [
"run_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}输出模式
{
"type": "object",
"properties": {
"object": {
"type": "string",
"const": "task_run"
},
"id": {
"type": "string"
},
"task_id": {
"type": "string"
},
"task_name": {
"type": [
"string",
"null"
]
},
"chat_id": {
"type": [
"string",
"null"
]
},
"status": {
"type": "string",
"enum": [
"pending",
"running",
"completed",
"failed",
"needs_input",
"timed_out",
"unknown",
"skipped"
]
},
"summary": {
"type": [
"string",
"null"
]
},
"error_message": {
"type": [
"string",
"null"
]
},
"pending_approval_ids": {
"type": "array",
"items": {
"type": "string"
}
},
"reused": {
"type": "boolean"
},
"wait_timed_out": {
"type": "boolean",
"description": "The wait ended first. The work is still running: follow it with the tool next_step names."
},
"next_step": {
"type": "string"
},
"credits_consumed": {
"type": "integer"
},
"started_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"completed_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"created_at": {
"type": "string",
"format": "date-time"
},
"result": {
"type": [
"string",
"null"
]
}
},
"required": [
"object",
"id",
"task_id",
"status",
"created_at"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"description": "A task run — one delegated job and what is known about its state."
}🟢get_run(run_id)
Fetch a run's current status, summary, pending approvals, and (once settled) the agent's final reply.
输入模式
{
"type": "object",
"properties": {
"run_id": {
"type": "string",
"description": "A run id (trun_...)."
}
},
"required": [
"run_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}输出模式
{
"type": "object",
"properties": {
"object": {
"type": "string",
"const": "task_run"
},
"id": {
"type": "string"
},
"task_id": {
"type": "string"
},
"task_name": {
"type": [
"string",
"null"
]
},
"chat_id": {
"type": [
"string",
"null"
]
},
"status": {
"type": "string",
"enum": [
"pending",
"running",
"completed",
"failed",
"needs_input",
"timed_out",
"unknown",
"skipped"
]
},
"summary": {
"type": [
"string",
"null"
]
},
"error_message": {
"type": [
"string",
"null"
]
},
"pending_approval_ids": {
"type": "array",
"items": {
"type": "string"
}
},
"reused": {
"type": "boolean"
},
"wait_timed_out": {
"type": "boolean",
"description": "The wait ended first. The work is still running: follow it with the tool next_step names."
},
"next_step": {
"type": "string"
},
"credits_consumed": {
"type": "integer"
},
"started_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"completed_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"created_at": {
"type": "string",
"format": "date-time"
},
"result": {
"type": [
"string",
"null"
]
}
},
"required": [
"object",
"id",
"task_id",
"status",
"created_at"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"description": "A task run — one delegated job and what is known about its state."
}🟢list_runs(status, task_id, limit, starting_after, ending_before)
List the account's task runs, newest first — delegated jobs and scheduled tasks alike. Filter by status or task.
输入模式
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"pending",
"running",
"completed",
"failed",
"needs_input",
"timed_out",
"unknown",
"skipped"
],
"description": "Only runs in this state."
},
"task_id": {
"type": "string",
"description": "Only runs of this task (task_...)."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"description": "Default 20."
},
"starting_after": {
"type": "string",
"description": "Return the page after this id — the last id from the previous page."
},
"ending_before": {
"type": "string",
"description": "Return the page before this id — the first id from the previous page."
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}输出模式
{
"type": "object",
"properties": {
"object": {
"type": "string",
"const": "list"
},
"data": {
"type": "array",
"items": {
"type": "object",
"description": "A task run — one delegated job and what is known about its state.",
"properties": {
"object": {
"type": "string",
"const": "task_run"
},
"id": {
"type": "string"
},
"task_id": {
"type": "string"
},
"task_name": {
"type": [
"string",
"null"
]
},
"chat_id": {
"type": [
"string",
"null"
]
},
"status": {
"type": "string",
"enum": [
"pending",
"running",
"completed",
"failed",
"needs_input",
"timed_out",
"unknown",
"skipped"
]
},
"summary": {
"type": [
"string",
"null"
]
},
"error_message": {
"type": [
"string",
"null"
]
},
"pending_approval_ids": {
"type": "array",
"items": {
"type": "string"
}
},
"reused": {
"type": "boolean"
},
"wait_timed_out": {
"type": "boolean",
"description": "The wait ended first. The work is still running: follow it with the tool next_step names."
},
"next_step": {
"type": "string"
},
"credits_consumed": {
"type": "integer"
},
"started_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"completed_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"created_at": {
"type": "string",
"format": "date-time"
},
"result": {
"type": [
"string",
"null"
]
}
},
"required": [
"object",
"id",
"task_id",
"status",
"created_at"
]
}
},
"has_more": {
"type": "boolean"
}
},
"required": [
"object",
"data",
"has_more"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"description": "A page of task runs, newest first."
}🔴resolve_approvals(run_id, approvals)
Approve or deny the integration actions a run is paused on (status needs_input with pending_approval_ids). Submit a decision for every pending id at once; the run resumes in the background.
输入模式
{
"type": "object",
"properties": {
"run_id": {
"type": "string",
"description": "A run id (trun_...)."
},
"approvals": {
"type": "array",
"description": "One decision per pending approval id — the run stays paused until every one is answered.",
"minItems": 1,
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "A pending approval id from the run's pending_approval_ids."
},
"approved": {
"type": "boolean",
"description": "True to let the action run, false to deny it."
},
"reason": {
"type": "string",
"description": "Why it was denied (optional)."
}
},
"required": [
"id",
"approved"
]
}
}
},
"required": [
"run_id",
"approvals"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}输出模式
{
"type": "object",
"properties": {
"object": {
"type": "string",
"const": "task_run"
},
"id": {
"type": "string"
},
"task_id": {
"type": "string"
},
"task_name": {
"type": [
"string",
"null"
]
},
"chat_id": {
"type": [
"string",
"null"
]
},
"status": {
"type": "string",
"enum": [
"pending",
"running",
"completed",
"failed",
"needs_input",
"timed_out",
"unknown",
"skipped"
]
},
"summary": {
"type": [
"string",
"null"
]
},
"error_message": {
"type": [
"string",
"null"
]
},
"pending_approval_ids": {
"type": "array",
"items": {
"type": "string"
}
},
"reused": {
"type": "boolean"
},
"wait_timed_out": {
"type": "boolean",
"description": "The wait ended first. The work is still running: follow it with the tool next_step names."
},
"next_step": {
"type": "string"
},
"credits_consumed": {
"type": "integer"
},
"started_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"completed_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"created_at": {
"type": "string",
"format": "date-time"
},
"result": {
"type": [
"string",
"null"
]
}
},
"required": [
"object",
"id",
"task_id",
"status",
"created_at"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"description": "A task run — one delegated job and what is known about its state."
}🔴cancel_run(run_id)
Stop a run that is pending, running, or waiting for input. The run is finalized as failed with 'Cancelled by the caller'.
输入模式
{
"type": "object",
"properties": {
"run_id": {
"type": "string",
"description": "A run id (trun_...)."
}
},
"required": [
"run_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}输出模式
{
"type": "object",
"properties": {
"object": {
"type": "string",
"const": "task_run"
},
"id": {
"type": "string"
},
"task_id": {
"type": "string"
},
"task_name": {
"type": [
"string",
"null"
]
},
"chat_id": {
"type": [
"string",
"null"
]
},
"status": {
"type": "string",
"enum": [
"pending",
"running",
"completed",
"failed",
"needs_input",
"timed_out",
"unknown",
"skipped"
]
},
"summary": {
"type": [
"string",
"null"
]
},
"error_message": {
"type": [
"string",
"null"
]
},
"pending_approval_ids": {
"type": "array",
"items": {
"type": "string"
}
},
"reused": {
"type": "boolean"
},
"wait_timed_out": {
"type": "boolean",
"description": "The wait ended first. The work is still running: follow it with the tool next_step names."
},
"next_step": {
"type": "string"
},
"credits_consumed": {
"type": "integer"
},
"started_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"completed_at": {
"type": [
"string",
"null"
],
"format": "date-time"
},
"created_at": {
"type": "string",
"format": "date-time"
},
"result": {
"type": [
"string",
"null"
]
}
},
"required": [
"object",
"id",
"task_id",
"status",
"created_at"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"description": "A task run — one delegated job and what is known about its state."
}推荐提示词
find_specific
Find [specific item] using Crevio
预期工具：
api_searchfetch_info
Fetch [information type] using Crevio
预期工具：
get_chatretrieve_data
Get details about [item] from Crevio
预期工具：
get_chatsearch_research
Search for information about [topic] using Crevio
预期工具：
api_searchlist_items
List all [items] available in Crevio
预期工具：
list_chats社区
证据
最近观测
已验证未记录版本18 个工具
已验证未记录版本14 个工具
已验证未记录版本14 个工具