// SCAN REPORT

CogniRepo

34 tools. 7 can modify or destroy data without limits.

6 write tools that can modify data. Rate limits recommended.

Last updated: 9 Jul 2026

7 can modify or destroy data

27 read-only

34 tools total

Community server · catalogue entry checked 09/07/2026

How to control CogniRepo ↓

TOOL MAP

What CogniRepo exposes to your agents

Read (27) Write / Execute (6) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous CogniRepo tools

Write · Medium link_repos With no description available, classification is based solely on the tool name. Write · Medium log_episode This tool writes/creates new records in the episodic memory store. Write · Medium record_decision The tool name implies writing a decision to persistent storage (consistent with the server's purpose of persistent memory and context). Write · Medium record_error The name 'record_error' implies creating or storing an error entry in persistent memory or knowledge graph (consistent with the server's purpose of persistent memory and context).

7 of CogniRepo's 34 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control CogniRepo

PolicyLayer is an MCP gateway — it sits between your AI agents and CogniRepo, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "link_repos": {
    "limits": [
      {
        "counter": "link_repos_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "architecture_overview": {
    "limits": [
      {
        "counter": "architecture_overview_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register CogniRepo — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON COGNIREPO →

Instant setup, no code required.

FULL CATALOGUE

All 34 CogniRepo tools

WRITE 6 tools

Write link_repos link_repos Write log_episode Log a structured episodic event to the episodic memory store. Write record_decision record_decision Write record_error record_error Write record_user_preference record_user_preference Write store_memory store_memory

READ 27 tools

Read architecture_overview Retrieve pre-computed architectural summaries. Read context_pack context_pack Read cross_repo_search cross_repo_search Read cross_repo_traverse cross_repo_traverse Read dependency_graph Return import/dependency relationships for a module. Read episodic_search Return past episodic events matching a keyword query. Read explain_change Explain what changed in a file or function recently by cross-referencing Read find_symbol_path find_symbol_path Read get_agent_bootstrap get_agent_bootstrap Read get_error_patterns get_error_patterns Read get_last_context get_last_context Read get_service_endpoints get_service_endpoints Read get_session_brief get_session_brief Read get_session_history get_session_history Read get_user_profile get_user_profile Read graph_stats Return a health summary of the current graph state. Read list_org_context list_org_context Read lookup_symbol lookup_symbol Read org_dependencies org_dependencies Read org_search org_search Read org_wide_search org_wide_search Read retrieve_memory Retrieve the top-k memories most similar to the query. Read search_docs Search indexed documentation files (.md, .rst, .txt) by semantic similarity. Read search_token search_token Read semantic_search_code semantic_search_code Read subgraph Return the local neighbourhood of a concept or symbol as {nodes, edges}. Read who_calls who_calls

OTHER 1 tools

Other supersede_learning supersede_learning

FAQ

Questions about CogniRepo

How do I prevent bulk modifications through CogniRepo? +

The CogniRepo server has 6 write tools including link_repos, log_episode, record_decision. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach CogniRepo.

How many tools does the CogniRepo MCP server expose? +

34 tools across 1 categories: Read. 27 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on CogniRepo? +

Register the CogniRepo MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every CogniRepo tool call.

Deterministic rules across all 34 CogniRepo tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON COGNIREPO →

Instant setup, no code required.

34 CogniRepo tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from CogniRepo's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →