ColossalCapital — Akashic Corpus & Agentic Platform
Akashic corpus + Laya routing. Anonymous read; free signup in-band.
我该使用它吗
质量与安全性
发现（2）
- LOWTool 'draft_deployment_plan' description lacks action verb在 draft_deployment_plan 中
- LOWTool 'fetch_hitl_items' suggests web access but openWorldHint=false在 fetch_hitl_items 中
基于对工具定义和协议合规性的自动分析。
上下文开销
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": {
"obvect": {
"url": "https://mcp.colossalcapital.co/mcp"
}
}
}远程端点
https://mcp.colossalcapital.co/mcpstreamable-http它能做什么
工具清单
工具（24）
🟢analyze_repo(repo_path, entity_id, interaction_id)
Trigger analysis on a repository. Returns the analysis run ID and status.
输入模式
{
"type": "object",
"properties": {
"repo_path": {
"title": "Repo Path",
"type": "string"
},
"entity_id": {
"default": "default",
"title": "Entity Id",
"type": "string"
},
"interaction_id": {
"default": "",
"title": "Interaction Id",
"type": "string"
}
},
"required": [
"repo_path"
],
"title": "analyze_repoArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "analyze_repoOutput"
}⚪draft_deployment_plan(workspace_id, source_repo, environment, derived_from_ticket, cicd_provider)
Draft a deployment plan from a ticket or repository. Returns the drafted plan with stages.
输入模式
{
"type": "object",
"properties": {
"workspace_id": {
"title": "Workspace Id",
"type": "string"
},
"source_repo": {
"title": "Source Repo",
"type": "string"
},
"environment": {
"default": "prod",
"title": "Environment",
"type": "string"
},
"derived_from_ticket": {
"default": "",
"title": "Derived From Ticket",
"type": "string"
},
"cicd_provider": {
"default": "",
"title": "Cicd Provider",
"type": "string"
}
},
"required": [
"workspace_id",
"source_repo"
],
"title": "draft_deployment_planArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "draft_deployment_planOutput"
}⚪generate_cicd_workflow(repo_path, provider, tier, build_command, test_command, ...)
Generate a CI/CD workflow (GitHub Actions, Bitbucket Pipelines, GitLab CI, or Tekton) with build, test, deploy, and callback stages. Returns YAML, filename, stages, and per-field research basis.
输入模式
{
"type": "object",
"properties": {
"repo_path": {
"title": "Repo Path",
"type": "string"
},
"provider": {
"title": "Provider",
"type": "string"
},
"tier": {
"default": "free",
"title": "Tier",
"type": "string"
},
"build_command": {
"default": "npm run build",
"title": "Build Command",
"type": "string"
},
"test_command": {
"default": "npm test",
"title": "Test Command",
"type": "string"
},
"deploy_enabled": {
"default": false,
"title": "Deploy Enabled",
"type": "boolean"
},
"deploy_environment": {
"default": "production",
"title": "Deploy Environment",
"type": "string"
}
},
"required": [
"repo_path",
"provider"
],
"title": "generate_cicd_workflowArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "generate_cicd_workflowOutput"
}🟡check_heartbeat_monitors(entity_id, trigger_check)
List heartbeat monitor status (8 condition-based monitors) or trigger a manual heartbeat check cycle. Monitors watch for PR merges, deploy failures, test failures, dependency drift, doc drift, security advisories, stale branches, and failing suites.
输入模式
{
"type": "object",
"properties": {
"entity_id": {
"default": "",
"title": "Entity Id",
"type": "string"
},
"trigger_check": {
"default": false,
"title": "Trigger Check",
"type": "boolean"
}
},
"title": "check_heartbeat_monitorsArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "check_heartbeat_monitorsOutput"
}🟢fetch_hitl_items(status, category)
Fetch pending HITL approval items with RBAC context (agent identity, caller role, required permission, and approval eligibility). Use this to check what needs human approval before proceeding.
输入模式
{
"type": "object",
"properties": {
"status": {
"default": "pending",
"title": "Status",
"type": "string"
},
"category": {
"default": "",
"title": "Category",
"type": "string"
}
},
"title": "fetch_hitl_itemsArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "fetch_hitl_itemsOutput"
}🟢search_skillfiles(query, persona)
Search for relevant skillfiles by query or persona. Skillfiles are the behavioral guidance layer for agents — they define how agents should write tests, create PRs, lint code, review, and generate CI/CD workflows.
输入模式
{
"type": "object",
"properties": {
"query": {
"default": "",
"title": "Query",
"type": "string"
},
"persona": {
"default": "",
"title": "Persona",
"type": "string"
}
},
"title": "search_skillfilesArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "search_skillfilesOutput"
}🟢get_research_basis(interaction_id)
Fetch the interaction chain for a given interaction ID, showing all artifacts (heartbeat, analysis, ticket, agent, PR, deployment) in the closed loop. If no interaction_id is provided, lists all known interaction IDs.
输入模式
{
"type": "object",
"properties": {
"interaction_id": {
"default": "",
"title": "Interaction Id",
"type": "string"
}
},
"title": "get_research_basisArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_research_basisOutput"
}🟢get_public_capabilities
Discover the ColossalCapital platform's public capabilities — fetches llms.txt. No account required. Use this first to learn what tools and APIs are available.
输入模式
{
"type": "object",
"properties": {},
"title": "get_public_capabilitiesArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_public_capabilitiesOutput"
}⚪register_account(email, name, intended_tier, use_case, captcha_token)
Register a free ColossalCapital account for a human user. Creates the identity immediately (free tier, no billing) and returns a link_token to claim the Idio login later. Call this when a tool returns account_required, or when a user asks to sign up.
输入模式
{
"type": "object",
"properties": {
"email": {
"title": "Email",
"type": "string"
},
"name": {
"title": "Name",
"type": "string"
},
"intended_tier": {
"default": "",
"title": "Intended Tier",
"type": "string"
},
"use_case": {
"default": "",
"title": "Use Case",
"type": "string"
},
"captcha_token": {
"default": "",
"title": "Captcha Token",
"type": "string"
}
},
"required": [
"email",
"name"
],
"title": "register_accountArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "register_accountOutput"
}⚪register_org(name, contact_email, contact_name, industry)
Register an organization account. Employees who signed up individually keep their accounts — org membership is added to them, never recreated. Returns the org's API key.
输入模式
{
"type": "object",
"properties": {
"name": {
"title": "Name",
"type": "string"
},
"contact_email": {
"title": "Contact Email",
"type": "string"
},
"contact_name": {
"default": "",
"title": "Contact Name",
"type": "string"
},
"industry": {
"default": "",
"title": "Industry",
"type": "string"
}
},
"required": [
"name",
"contact_email"
],
"title": "register_orgArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "register_orgOutput"
}⚪register_agent(name, ed25519_pubkey, operator_contact, intended_use)
Register an autonomous agent as a first-class account (entity_type=agent). The Ed25519 public key is the only credential — no password. Gets a prepaid wallet for metered tools. Can later be bound to a user via claim_agent without losing its identity.
输入模式
{
"type": "object",
"properties": {
"name": {
"title": "Name",
"type": "string"
},
"ed25519_pubkey": {
"title": "Ed25519 Pubkey",
"type": "string"
},
"operator_contact": {
"default": "",
"title": "Operator Contact",
"type": "string"
},
"intended_use": {
"default": "",
"title": "Intended Use",
"type": "string"
}
},
"required": [
"name",
"ed25519_pubkey"
],
"title": "register_agentArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "register_agentOutput"
}⚪claim_agent(agent_id, claimant_entity_id, signature, scopes, workspace_scope)
Bind a registered agent to a user or org account so it acts on their behalf (acted_for grant). Requires a signature from the agent over claim:{agent_id}:{entity_id} — the agent consents, and the account consents. The agent keeps its own identity.
输入模式
{
"type": "object",
"properties": {
"agent_id": {
"title": "Agent Id",
"type": "string"
},
"claimant_entity_id": {
"title": "Claimant Entity Id",
"type": "string"
},
"signature": {
"title": "Signature",
"type": "string"
},
"scopes": {
"default": "",
"title": "Scopes",
"type": "string"
},
"workspace_scope": {
"default": "",
"title": "Workspace Scope",
"type": "string"
}
},
"required": [
"agent_id",
"claimant_entity_id",
"signature"
],
"title": "claim_agentArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "claim_agentOutput"
}🟢search_corpus(query, stack_layer, technology, limit)
Search the Akashic corpus — the platform's knowledge base of tools, stack layers, design patterns, and exemplars. Public entries only; no account required. Register via register_account or register_agent for the full corpus.
输入模式
{
"type": "object",
"properties": {
"query": {
"default": "",
"title": "Query",
"type": "string"
},
"stack_layer": {
"default": "",
"title": "Stack Layer",
"type": "string"
},
"technology": {
"default": "",
"title": "Technology",
"type": "string"
},
"limit": {
"default": 20,
"title": "Limit",
"type": "integer"
}
},
"title": "search_corpusArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "search_corpusOutput"
}🟢read_corpus_item(entry_id)
Read a public Akashic corpus item in full. Items above the public class return an account_required pointer.
输入模式
{
"type": "object",
"properties": {
"entry_id": {
"title": "Entry Id",
"type": "string"
}
},
"required": [
"entry_id"
],
"title": "read_corpus_itemArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "read_corpus_itemOutput"
}🟢corpus_route(task, domain)
Route a task through Laya to the best corpus item — returns the decision kind, picked item, score, and citations. Items above your visibility class return an account_required pointer.
输入模式
{
"type": "object",
"properties": {
"task": {
"title": "Task",
"type": "string"
},
"domain": {
"default": "general",
"title": "Domain",
"type": "string"
}
},
"required": [
"task"
],
"title": "corpus_routeArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "corpus_routeOutput"
}🟢corpus_domains(product)
List the corpus domain lanes (261 domains of repos, docs, code examples, issues) with item counts — the discovery index for corpus_route and corpus_item.
输入模式
{
"type": "object",
"properties": {
"product": {
"default": "",
"title": "Product",
"type": "string"
}
},
"title": "corpus_domainsArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "corpus_domainsOutput"
}🟢corpus_item(item_id)
Read one corpus item's full record — evidence, license, quality, tags. Items above your visibility class return an account_required pointer.
输入模式
{
"type": "object",
"properties": {
"item_id": {
"title": "Item Id",
"type": "string"
}
},
"required": [
"item_id"
],
"title": "corpus_itemArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "corpus_itemOutput"
}🟢corpus_outcome(item_id, domain, success, note)
Report whether a cited corpus item helped — feeds Laya's routing flywheel so the corpus improves with use. Anonymous reports count at reduced weight.
输入模式
{
"type": "object",
"properties": {
"item_id": {
"title": "Item Id",
"type": "string"
},
"domain": {
"title": "Domain",
"type": "string"
},
"success": {
"title": "Success",
"type": "boolean"
},
"note": {
"default": "",
"title": "Note",
"type": "string"
}
},
"required": [
"item_id",
"domain",
"success"
],
"title": "corpus_outcomeArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "corpus_outcomeOutput"
}🟢get_onboarding_guide
Returns the canonical onboarding flow for every caller class — anonymous, human signup, autonomous agent, agent binding, and org creation. Call this first if you're unsure how to proceed.
输入模式
{
"type": "object",
"properties": {},
"title": "get_onboarding_guideArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_onboarding_guideOutput"
}🟢list_llm_providers
List LLM providers you can bring keys for (BYOK). The platform runs on your keys — inference cost is yours, ours is the routing.
输入模式
{
"type": "object",
"properties": {},
"title": "list_llm_providersArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "list_llm_providersOutput"
}🟡set_llm_key(provider, api_key, scope, validate)
Store a BYOK LLM provider key in the encrypted vault. Validated against the provider before storing. scope='org' stores an org-wide key (admin-only). Requires an account — call register_account or authenticate first.
输入模式
{
"type": "object",
"properties": {
"provider": {
"title": "Provider",
"type": "string"
},
"api_key": {
"title": "Api Key",
"type": "string"
},
"scope": {
"default": "entity",
"title": "Scope",
"type": "string"
},
"validate": {
"default": true,
"title": "Validate",
"type": "boolean"
}
},
"required": [
"provider",
"api_key"
],
"title": "set_llm_keyArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "set_llm_keyOutput"
}🟢list_llm_keys
List which LLM providers have stored keys (never the keys themselves). Use to check BYOK configuration status.
输入模式
{
"type": "object",
"properties": {},
"title": "list_llm_keysArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "list_llm_keysOutput"
}🔴remove_llm_key(provider, scope)
Remove a stored BYOK provider key from the vault.
输入模式
{
"type": "object",
"properties": {
"provider": {
"title": "Provider",
"type": "string"
},
"scope": {
"default": "entity",
"title": "Scope",
"type": "string"
}
},
"required": [
"provider"
],
"title": "remove_llm_keyArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "remove_llm_keyOutput"
}🟢test_llm_key(provider, api_key)
Test an LLM provider key against the provider without storing it. Use before set_llm_key if you want to check validity first.
输入模式
{
"type": "object",
"properties": {
"provider": {
"title": "Provider",
"type": "string"
},
"api_key": {
"title": "Api Key",
"type": "string"
}
},
"required": [
"provider",
"api_key"
],
"title": "test_llm_keyArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "test_llm_keyOutput"
}社区
证据