Webhook Studio

Keyless webhook endpoints: capture, wait, replay, forward, and generate types from real traffic.

我該用這個嗎

品質與安全性

A
說明品質
99%
結構描述完整度
98%
命名品質
95%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

根據工具定義與協定合規性的自動化分析。

上下文成本

~2,709Token(工具定義)
~1.2 KB典型回應大小
顯著的注意力影響(128k 上下文的 2.12%)

這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高,可用於其他工作的注意力就越少。

安裝

一鍵安裝

將以下內容加入你的 `claude_desktop_config.json` 檔案:

{
  "mcpServers": {
    "webhooks": {
      "url": "https://webhook-studio.com/mcp"
    }
  }
}

遠端端點

https://webhook-studio.com/mcpstreamable-http

它能做什麼

工具清單

工具(17)

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟡create_bucket(name, environment, external_ref)

Provision a new webhook endpoint (a "bucket") that captures incoming HTTP requests. Returns its id, public ingest url to point a provider at, inbox_url (the live human view to hand back), and signing secret. Pass external_ref — your own stable name like "acme-api:stripe" — so you can re-find this exact bucket later with list_buckets after losing context.

輸入結構描述

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Human label for the bucket."
    },
    "environment": {
      "type": "string",
      "description": "Deployment environment.",
      "enum": [
        "production",
        "staging",
        "sandbox",
        "development"
      ]
    },
    "external_ref": {
      "type": "string",
      "description": "Your own stable identifier (unique per account) for idempotent re-provisioning and re-finding."
    }
  },
  "required": [],
  "additionalProperties": false
}
🟢list_buckets(external_ref)

List your webhook endpoints. Pass external_ref to fetch the specific bucket you created earlier under that name — this is how you re-anchor after losing the conversation, since you never need to have stored the bucket id.

輸入結構描述

{
  "type": "object",
  "properties": {
    "external_ref": {
      "type": "string",
      "description": "Return only the bucket with this exact external_ref."
    }
  },
  "required": [],
  "additionalProperties": false
}
🟢get_bucket(bucket_id)

Fetch one webhook endpoint by id, including its url and inbox_url.

輸入結構描述

{
  "type": "object",
  "properties": {
    "bucket_id": {
      "type": "string",
      "description": "The endpoint id."
    }
  },
  "required": [
    "bucket_id"
  ],
  "additionalProperties": false
}
🔴delete_bucket(bucket_id)

Permanently delete a webhook endpoint and its captured events.

輸入結構描述

{
  "type": "object",
  "properties": {
    "bucket_id": {
      "type": "string",
      "description": "The endpoint id."
    }
  },
  "required": [
    "bucket_id"
  ],
  "additionalProperties": false
}
🟡latest_event(bucket_id, provider, type)

Get the single most recent event captured by a bucket, optionally filtered by provider and event type. Returns one event with its headers, body and delivery results — the one-shot answer to "what did Stripe last send me". 404 if nothing matches, so you never index into an empty list.

輸入結構描述

{
  "type": "object",
  "properties": {
    "bucket_id": {
      "type": "string",
      "description": "The endpoint id."
    },
    "provider": {
      "type": "string",
      "description": "Filter to a provider attributed at ingest (e.g. stripe, github)."
    },
    "type": {
      "type": "string",
      "description": "The provider's own event name, matched exactly (e.g. payment_intent.succeeded)."
    }
  },
  "required": [
    "bucket_id"
  ],
  "additionalProperties": false
}
🟢list_events(bucket_id, since, until, provider, type, ...)

List events captured by a bucket, newest first, with composable filters: since/until (ISO 8601 or YYYY-MM-DD), provider, type, method, signature_valid, and q (case-insensitive substring over body, content type, method, type and labels). Use cursor for the next page.

輸入結構描述

{
  "type": "object",
  "properties": {
    "bucket_id": {
      "type": "string",
      "description": "The endpoint id."
    },
    "since": {
      "type": "string",
      "description": "Only events at or after this time (ISO 8601 or YYYY-MM-DD)."
    },
    "until": {
      "type": "string",
      "description": "Only events at or before this time."
    },
    "provider": {
      "type": "string",
      "description": "Filter to a provider (e.g. stripe, github)."
    },
    "type": {
      "type": "string",
      "description": "The provider's own event name, matched exactly."
    },
    "method": {
      "type": "string",
      "description": "HTTP method (GET, POST, ...)."
    },
    "signature_valid": {
      "type": "boolean",
      "description": "Only events whose signature verification passed/failed."
    },
    "q": {
      "type": "string",
      "description": "Case-insensitive substring search over body/content-type/method/type/labels."
    },
    "limit": {
      "type": "number",
      "description": "Max events to return (1–100, default 20)."
    },
    "cursor": {
      "type": "string",
      "description": "Pagination cursor from a previous response."
    }
  },
  "required": [
    "bucket_id"
  ],
  "additionalProperties": false
}
🟢get_event(event_id)

Fetch one captured event by id with its full headers, body, signature verification result (and failure reason), and every outbound delivery attempt. This is how you find out whether your forward actually reached its target and what came back.

輸入結構描述

{
  "type": "object",
  "properties": {
    "event_id": {
      "type": "string",
      "description": "The event id."
    }
  },
  "required": [
    "event_id"
  ],
  "additionalProperties": false
}
🟡wait_for_event(bucket_id, timeout, provider, type)

Block until the next matching event arrives on a bucket, or until the timeout. Use this to turn "go click Send test webhook in Stripe" into a synchronous step: call it, tell the human to trigger the event, and it returns as soon as one arrives. Filters (provider, type) mean unrelated traffic does not wake it. Returns the event, or nothing if it times out.

輸入結構描述

{
  "type": "object",
  "properties": {
    "bucket_id": {
      "type": "string",
      "description": "The endpoint id."
    },
    "timeout": {
      "type": "number",
      "description": "Seconds to wait (1–55, default 30)."
    },
    "provider": {
      "type": "string",
      "description": "Only resolve on an event from this provider."
    },
    "type": {
      "type": "string",
      "description": "Only resolve on this event type."
    }
  },
  "required": [
    "bucket_id"
  ],
  "additionalProperties": false
}
🟡replay_event(event_id, url, preserve_headers, headers, body, ...)

Re-send a captured event to any URL — the test runner for a handler you just wrote. preserve_headers defaults to true so the original signature header (e.g. Stripe-Signature) arrives intact. If you changed the body or the receiver verifies with a different secret, pass resign_with (the dev's own signing secret) so the payload is re-signed and their verification code passes unmodified. Returns the response status, latency and body.

輸入結構描述

{
  "type": "object",
  "properties": {
    "event_id": {
      "type": "string",
      "description": "The event id to replay."
    },
    "url": {
      "type": "string",
      "description": "Destination URL to send it to."
    },
    "preserve_headers": {
      "type": "boolean",
      "description": "Replay the captured headers verbatim (default true)."
    },
    "headers": {
      "type": "object",
      "description": "Header overrides layered on top of the preserved set."
    },
    "body": {
      "type": "string",
      "description": "Replacement request body (defaults to the captured body)."
    },
    "resign_with": {
      "type": "string",
      "description": "Signing secret to re-sign the payload with (≥16 chars)."
    },
    "signature_header": {
      "type": "string",
      "description": "Header name for resign_with (default x-signature)."
    }
  },
  "required": [
    "event_id",
    "url"
  ],
  "additionalProperties": false
}
🟡forward_bucket(bucket_id, url, name, forward_all, condition_tree, ...)

Set up standing forwarding from a bucket to a URL. Pass forward_all:true to forward every event, or condition_tree to forward only matching events (same AND/OR condition grammar the routing engine uses). Creates the destination and routing rule in one call.

輸入結構描述

{
  "type": "object",
  "properties": {
    "bucket_id": {
      "type": "string",
      "description": "The endpoint id."
    },
    "url": {
      "type": "string",
      "description": "Destination URL to forward to."
    },
    "name": {
      "type": "string",
      "description": "Optional label for the destination."
    },
    "forward_all": {
      "type": "boolean",
      "description": "Forward every event unconditionally."
    },
    "condition_tree": {
      "type": "object",
      "description": "A condition tree (AND/OR of field comparisons) to forward only matching events. Mutually exclusive with forward_all."
    },
    "rule_name": {
      "type": "string",
      "description": "Optional name for the routing rule when using condition_tree."
    }
  },
  "required": [
    "bucket_id",
    "url"
  ],
  "additionalProperties": false
}
🟢list_deliveries(bucket_id, success, source, limit, cursor)

List outbound delivery attempts for a bucket, newest first, with the full request and response of each. Pass success:false to see only failures — the direct answer to "which of my forwards are broken and why".

輸入結構描述

{
  "type": "object",
  "properties": {
    "bucket_id": {
      "type": "string",
      "description": "The endpoint id."
    },
    "success": {
      "type": "boolean",
      "description": "Filter to succeeded (true) or failed (false) deliveries."
    },
    "source": {
      "type": "string",
      "description": "Delivery source.",
      "enum": [
        "rule",
        "replay",
        "manual_test"
      ]
    },
    "limit": {
      "type": "number",
      "description": "Max deliveries to return (1–100, default 20)."
    },
    "cursor": {
      "type": "string",
      "description": "Pagination cursor from a previous response."
    }
  },
  "required": [
    "bucket_id"
  ],
  "additionalProperties": false
}
🟡configure_verification(bucket_id, secret, hmac_enabled, header_name, tolerance_seconds, ...)

Turn on HMAC signature verification for a bucket using the provider's own signing secret (e.g. Stripe's whsec_). This is how you finish a "verified webhook" integration end to end. Set secret to the provider secret and hmac_enabled:true in the same call; the signature scheme is auto-detected from the header shape.

輸入結構描述

{
  "type": "object",
  "properties": {
    "bucket_id": {
      "type": "string",
      "description": "The endpoint id."
    },
    "secret": {
      "type": "string",
      "description": "The provider's signing secret (≥16 chars)."
    },
    "hmac_enabled": {
      "type": "boolean",
      "description": "Enable verification."
    },
    "header_name": {
      "type": "string",
      "description": "Signature header to read (auto-detected if omitted)."
    },
    "tolerance_seconds": {
      "type": "number",
      "description": "Max timestamp skew allowed, in seconds."
    },
    "on_failure": {
      "type": "string",
      "description": "What to do with a failed signature.",
      "enum": [
        "reject",
        "accept_log"
      ]
    }
  },
  "required": [
    "bucket_id"
  ],
  "additionalProperties": false
}
🟢list_schemas(provider, event_type)

List the payload schemas Webhook Studio has learned from this account's real traffic, optionally filtered by provider and event_type. These outlive the payloads they were learned from, so this answers "what shapes do I know about" even after old events are gone. Start here to discover what you can generate types or diffs for.

輸入結構描述

{
  "type": "object",
  "properties": {
    "provider": {
      "type": "string",
      "description": "Filter to a provider."
    },
    "event_type": {
      "type": "string",
      "description": "The provider's own event name."
    }
  },
  "required": [],
  "additionalProperties": false
}
🟢get_schema(schema_id, version)

Fetch one learned schema with every field, its type, whether it is optional, and how often it actually appears — the real shape of the payload, derived from what this account received rather than guessed from training data.

輸入結構描述

{
  "type": "object",
  "properties": {
    "schema_id": {
      "type": "string",
      "description": "The schema id."
    },
    "version": {
      "type": "string",
      "description": "Version number, or \"current\" (the default)."
    }
  },
  "required": [
    "schema_id"
  ],
  "additionalProperties": false
}
🟢diff_schema(schema_id, from, to)

Compare two versions of a learned schema and get exactly which fields were added, removed or changed type, each flagged as breaking or not. This is the "why did my handler start failing" answer, produced without reading a single payload. from defaults to the version before to.

輸入結構描述

{
  "type": "object",
  "properties": {
    "schema_id": {
      "type": "string",
      "description": "The schema id."
    },
    "from": {
      "type": "string",
      "description": "Baseline version number (defaults to the one before \"to\")."
    },
    "to": {
      "type": "string",
      "description": "Target version number, or \"current\"."
    }
  },
  "required": [
    "schema_id"
  ],
  "additionalProperties": false
}
⚪generate_types(schema_id, lang, framework, version)

Generate types, a runtime validator, or a full handler from a learned schema — the payoff of the knowledge layer. Everything is derived from the payloads this account ACTUALLY received, with genuinely-optional fields marked optional, instead of a plausible-but-wrong guess from a model's memory of the provider docs. Pass lang for a bare type (typescript / json-schema / zod), or framework (next / express) for a ready-to-paste handler that validates and hands back a fully-typed event.

輸入結構描述

{
  "type": "object",
  "properties": {
    "schema_id": {
      "type": "string",
      "description": "The schema id."
    },
    "lang": {
      "type": "string",
      "description": "Output format for a bare type.",
      "enum": [
        "typescript",
        "json-schema",
        "zod"
      ]
    },
    "framework": {
      "type": "string",
      "description": "Return a ready-to-paste handler scaffold instead of a bare type. Overrides lang.",
      "enum": [
        "next",
        "express"
      ]
    },
    "version": {
      "type": "string",
      "description": "Version number, or \"current\" (the default)."
    }
  },
  "required": [
    "schema_id"
  ],
  "additionalProperties": false
}
🟢find_correlation_keys(schema_id, version)

List the correlation-key candidates for a learned schema — the fields that look like identifiers (e.g. data.object.id), ranked by how consistently they appear. These are the fields to group events by when reconstructing a lifecycle (a Stripe payment_intent across created -> succeeded, a GitHub PR across its events). Derived from real traffic, so it reflects what THIS account actually receives.

輸入結構描述

{
  "type": "object",
  "properties": {
    "schema_id": {
      "type": "string",
      "description": "The schema id."
    },
    "version": {
      "type": "string",
      "description": "Version number, or \"current\" (the default)."
    }
  },
  "required": [
    "schema_id"
  ],
  "additionalProperties": false
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本17 個工具
已驗證未記錄版本17 個工具