Servers Playground How we check Add a server Log in

ColossalCapital — Akashic Corpus & Agentic Platform

Working · 7.0 s

co.colossalcapital/obvectv1.0.1 Domain verified

Akashic corpus + Laya routing. Anonymous read; free signup in-band.

AI & Agents

Registry entry

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://mcp.colossalcapital.co/mcp

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

analyze_repo

Trigger analysis on a repository. Returns the analysis run ID and status.

repo_pathstring, required

entity_idstring

interaction_idstring

This tool isn't marked read-only, so it may change something on the server or in an account you connected.

I understand, run it anyway

ColossalCapital — Akashic Corpus & Agentic Platform MCP server | mcptry

Tools (24)

analyze_repo

Trigger analysis on a repository. Returns the analysis run ID and status.

Argument	Type	Description
entity_id	string
repo_path*	string
interaction_id	string

Input schema (JSON)

{
  "type": "object",
  "title": "analyze_repoArguments",
  "required": [
    "repo_path"
  ],
  "properties": {
    "entity_id": {
      "type": "string",
      "title": "Entity Id",
      "default": "default"
    },
    "repo_path": {
      "type": "string",
      "title": "Repo Path"
    },
    "interaction_id": {
      "type": "string",
      "title": "Interaction Id",
      "default": ""
    }
  }
}

check_heartbeat_monitors

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.

Argument	Type	Description
entity_id	string
trigger_check	boolean

Input schema (JSON)

{
  "type": "object",
  "title": "check_heartbeat_monitorsArguments",
  "properties": {
    "entity_id": {
      "type": "string",
      "title": "Entity Id",
      "default": ""
    },
    "trigger_check": {
      "type": "boolean",
      "title": "Trigger Check",
      "default": false
    }
  }
}

claim_agent

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.

Argument	Type	Description
scopes	string
agent_id*	string
signature*	string
workspace_scope	string
claimant_entity_id*	string

Input schema (JSON)

{
  "type": "object",
  "title": "claim_agentArguments",
  "required": [
    "agent_id",
    "claimant_entity_id",
    "signature"
  ],
  "properties": {
    "scopes": {
      "type": "string",
      "title": "Scopes",
      "default": ""
    },
    "agent_id": {
      "type": "string",
      "title": "Agent Id"
    },
    "signature": {
      "type": "string",
      "title": "Signature"
    },
    "workspace_scope": {
      "type": "string",
      "title": "Workspace Scope",
      "default": ""
    },
    "claimant_entity_id": {
      "type": "string",
      "title": "Claimant Entity Id"
    }
  }
}

corpus_domains

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.

read-only

Argument	Type	Description
product	string

Input schema (JSON)

{
  "type": "object",
  "title": "corpus_domainsArguments",
  "properties": {
    "product": {
      "type": "string",
      "title": "Product",
      "default": ""
    }
  }
}

corpus_item

Read one corpus item's full record — evidence, license, quality, tags. Items above your visibility class return an account_required pointer.

read-only

Argument	Type	Description
item_id*	string

Input schema (JSON)

{
  "type": "object",
  "title": "corpus_itemArguments",
  "required": [
    "item_id"
  ],
  "properties": {
    "item_id": {
      "type": "string",
      "title": "Item Id"
    }
  }
}

corpus_outcome

Report whether a cited corpus item helped — feeds Laya's routing flywheel so the corpus improves with use. Anonymous reports count at reduced weight.

Argument	Type	Description
note	string
domain*	string
item_id*	string
success*	boolean

Input schema (JSON)

{
  "type": "object",
  "title": "corpus_outcomeArguments",
  "required": [
    "item_id",
    "domain",
    "success"
  ],
  "properties": {
    "note": {
      "type": "string",
      "title": "Note",
      "default": ""
    },
    "domain": {
      "type": "string",
      "title": "Domain"
    },
    "item_id": {
      "type": "string",
      "title": "Item Id"
    },
    "success": {
      "type": "boolean",
      "title": "Success"
    }
  }
}

corpus_route

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.

read-only

Argument	Type	Description
task*	string
domain	string

Input schema (JSON)

{
  "type": "object",
  "title": "corpus_routeArguments",
  "required": [
    "task"
  ],
  "properties": {
    "task": {
      "type": "string",
      "title": "Task"
    },
    "domain": {
      "type": "string",
      "title": "Domain",
      "default": "general"
    }
  }
}

draft_deployment_plan

Draft a deployment plan from a ticket or repository. Returns the drafted plan with stages.

Argument	Type	Description
environment	string
source_repo*	string
workspace_id*	string
cicd_provider	string
derived_from_ticket	string

Input schema (JSON)

{
  "type": "object",
  "title": "draft_deployment_planArguments",
  "required": [
    "workspace_id",
    "source_repo"
  ],
  "properties": {
    "environment": {
      "type": "string",
      "title": "Environment",
      "default": "prod"
    },
    "source_repo": {
      "type": "string",
      "title": "Source Repo"
    },
    "workspace_id": {
      "type": "string",
      "title": "Workspace Id"
    },
    "cicd_provider": {
      "type": "string",
      "title": "Cicd Provider",
      "default": ""
    },
    "derived_from_ticket": {
      "type": "string",
      "title": "Derived From Ticket",
      "default": ""
    }
  }
}

fetch_hitl_items

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.

read-only

Argument	Type	Description
status	string
category	string

Input schema (JSON)

{
  "type": "object",
  "title": "fetch_hitl_itemsArguments",
  "properties": {
    "status": {
      "type": "string",
      "title": "Status",
      "default": "pending"
    },
    "category": {
      "type": "string",
      "title": "Category",
      "default": ""
    }
  }
}

generate_cicd_workflow

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.

Argument	Type	Description
tier	string
provider*	string
repo_path*	string
test_command	string
build_command	string
deploy_enabled	boolean
deploy_environment	string

Input schema (JSON)

{
  "type": "object",
  "title": "generate_cicd_workflowArguments",
  "required": [
    "repo_path",
    "provider"
  ],
  "properties": {
    "tier": {
      "type": "string",
      "title": "Tier",
      "default": "free"
    },
    "provider": {
      "type": "string",
      "title": "Provider"
    },
    "repo_path": {
      "type": "string",
      "title": "Repo Path"
    },
    "test_command": {
      "type": "string",
      "title": "Test Command",
      "default": "npm test"
    },
    "build_command": {
      "type": "string",
      "title": "Build Command",
      "default": "npm run build"
    },
    "deploy_enabled": {
      "type": "boolean",
      "title": "Deploy Enabled",
      "default": false
    },
    "deploy_environment": {
      "type": "string",
      "title": "Deploy Environment",
      "default": "production"
    }
  }
}

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.

read-only

No arguments.

Input schema (JSON)

{
  "type": "object",
  "title": "get_onboarding_guideArguments",
  "properties": {}
}

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.

read-only

No arguments.

Input schema (JSON)

{
  "type": "object",
  "title": "get_public_capabilitiesArguments",
  "properties": {}
}

get_research_basis

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.

read-only

Argument	Type	Description
interaction_id	string

Input schema (JSON)

{
  "type": "object",
  "title": "get_research_basisArguments",
  "properties": {
    "interaction_id": {
      "type": "string",
      "title": "Interaction Id",
      "default": ""
    }
  }
}

list_llm_keys

List which LLM providers have stored keys (never the keys themselves). Use to check BYOK configuration status.

read-only

No arguments.

Input schema (JSON)

{
  "type": "object",
  "title": "list_llm_keysArguments",
  "properties": {}
}

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.

read-only

No arguments.

Input schema (JSON)

{
  "type": "object",
  "title": "list_llm_providersArguments",
  "properties": {}
}

read_corpus_item

Read a public Akashic corpus item in full. Items above the public class return an account_required pointer.

read-only

Argument	Type	Description
entry_id*	string

Input schema (JSON)

{
  "type": "object",
  "title": "read_corpus_itemArguments",
  "required": [
    "entry_id"
  ],
  "properties": {
    "entry_id": {
      "type": "string",
      "title": "Entry Id"
    }
  }
}

register_account

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.

Argument	Type	Description
name*	string
email*	string
use_case	string
captcha_token	string
intended_tier	string

Input schema (JSON)

{
  "type": "object",
  "title": "register_accountArguments",
  "required": [
    "email",
    "name"
  ],
  "properties": {
    "name": {
      "type": "string",
      "title": "Name"
    },
    "email": {
      "type": "string",
      "title": "Email"
    },
    "use_case": {
      "type": "string",
      "title": "Use Case",
      "default": ""
    },
    "captcha_token": {
      "type": "string",
      "title": "Captcha Token",
      "default": ""
    },
    "intended_tier": {
      "type": "string",
      "title": "Intended Tier",
      "default": ""
    }
  }
}

register_agent

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.

Argument	Type	Description
name*	string
intended_use	string
ed25519_pubkey*	string
operator_contact	string

Input schema (JSON)

{
  "type": "object",
  "title": "register_agentArguments",
  "required": [
    "name",
    "ed25519_pubkey"
  ],
  "properties": {
    "name": {
      "type": "string",
      "title": "Name"
    },
    "intended_use": {
      "type": "string",
      "title": "Intended Use",
      "default": ""
    },
    "ed25519_pubkey": {
      "type": "string",
      "title": "Ed25519 Pubkey"
    },
    "operator_contact": {
      "type": "string",
      "title": "Operator Contact",
      "default": ""
    }
  }
}

register_org

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.

Argument	Type	Description
name*	string
industry	string
contact_name	string
contact_email*	string

Input schema (JSON)

{
  "type": "object",
  "title": "register_orgArguments",
  "required": [
    "name",
    "contact_email"
  ],
  "properties": {
    "name": {
      "type": "string",
      "title": "Name"
    },
    "industry": {
      "type": "string",
      "title": "Industry",
      "default": ""
    },
    "contact_name": {
      "type": "string",
      "title": "Contact Name",
      "default": ""
    },
    "contact_email": {
      "type": "string",
      "title": "Contact Email"
    }
  }
}

remove_llm_key

Remove a stored BYOK provider key from the vault.

destructive

Argument	Type	Description
scope	string
provider*	string

Input schema (JSON)

{
  "type": "object",
  "title": "remove_llm_keyArguments",
  "required": [
    "provider"
  ],
  "properties": {
    "scope": {
      "type": "string",
      "title": "Scope",
      "default": "entity"
    },
    "provider": {
      "type": "string",
      "title": "Provider"
    }
  }
}

search_corpus

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.

read-only

Argument	Type	Description
limit	integer
query	string
technology	string
stack_layer	string

Input schema (JSON)

{
  "type": "object",
  "title": "search_corpusArguments",
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 20
    },
    "query": {
      "type": "string",
      "title": "Query",
      "default": ""
    },
    "technology": {
      "type": "string",
      "title": "Technology",
      "default": ""
    },
    "stack_layer": {
      "type": "string",
      "title": "Stack Layer",
      "default": ""
    }
  }
}

search_skillfiles

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.

read-only

Argument	Type	Description
query	string
persona	string

Input schema (JSON)

{
  "type": "object",
  "title": "search_skillfilesArguments",
  "properties": {
    "query": {
      "type": "string",
      "title": "Query",
      "default": ""
    },
    "persona": {
      "type": "string",
      "title": "Persona",
      "default": ""
    }
  }
}

set_llm_key

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.

Argument	Type	Description
scope	string
api_key*	string
provider*	string
validate	boolean

Input schema (JSON)

{
  "type": "object",
  "title": "set_llm_keyArguments",
  "required": [
    "provider",
    "api_key"
  ],
  "properties": {
    "scope": {
      "type": "string",
      "title": "Scope",
      "default": "entity"
    },
    "api_key": {
      "type": "string",
      "title": "Api Key"
    },
    "provider": {
      "type": "string",
      "title": "Provider"
    },
    "validate": {
      "type": "boolean",
      "title": "Validate",
      "default": true
    }
  }
}

test_llm_key

Test an LLM provider key against the provider without storing it. Use before set_llm_key if you want to check validity first.

read-only

Argument	Type	Description
api_key*	string
provider*	string

Input schema (JSON)

{
  "type": "object",
  "title": "test_llm_keyArguments",
  "required": [
    "provider",
    "api_key"
  ],
  "properties": {
    "api_key": {
      "type": "string",
      "title": "Api Key"
    },
    "provider": {
      "type": "string",
      "title": "Provider"
    }
  }
}