CogniRepo MCP server

Read from the package source without running it. The installed server may list more.

• architecture_overview

  Retrieve pre-computed architectural summaries. scope: 'root' for repo summary, a directory path, or a file path.

• context_pack

  Budget-pack the most relevant code + episodic context into a token-bounded block ready for injection into the next prompt. Call this BEFORE reading any source file to avoid wasting tokens on raw file reads. Returns at most max_tokens (default 2000) tokens — much smaller than raw files. Do NOT call for known short files (< 50 lines) — use Read directly instead.

• cross_repo_search

  Search knowledge from sibling repositories.

• cross_repo_traverse

  Traverse the org dependency graph from a repo or symbol to find cross-service relationships.

• dependency_graph

  Return import/dependency relationships for a module. direction: "imports" | "imported_by" | "both". depth: transitive traversal depth (1 = direct only).

• episodic_search

  Return past episodic events matching a keyword query.

• explain_change

  Explain what changed in a file or function recently by cross-referencing git history with episodic memory events mentioning the same target.

• find_symbol_path

  Find the shortest call-graph path between two symbols, crossing service boundaries via the org graph when needed.

• get_agent_bootstrap

  Single-call session bootstrap for AI agents. Replaces the 4-call sequence (get_session_brief → get_last_context → get_user_profile → get_error_patterns) with one ~300-token payload.

• get_error_patterns

  Return recurring error patterns with prevention hints to avoid repeating mistakes.

• get_last_context

  Return the most recent context snapshot written by context_pack.

• get_service_endpoints

  Return the HTTP endpoint registry for a service (from endpoints.json).

• get_session_brief

  Generate a session bootstrap brief for agent orientation.

• get_session_history

  Return recent conversation session exchanges for context continuity.

• get_user_profile

  Return the user's interaction style profile for Claude to adapt its responses.

• graph_stats

  Return a health summary of the current graph state.

• link_repos

  Record a dependency relationship between two repos in the org graph. Call this when you discover that one repo imports from or calls another.

• list_org_context

  Show what org, project, and sibling repositories the current repo belongs to.

• log_episode

  Log a structured episodic event to the episodic memory store. Use to record what happened: bugs found, code explored, agent actions. Retrievable via episodic_search in future sessions. Do NOT use for architectural decisions — use record_decision instead.

• lookup_symbol

  Return all locations where a symbol is defined or called, with file, line, and type. If include_org=True, also searches sibling repositories in the same organization. Do NOT call for broad concepts — only exact or near-exact symbol names. For concept queries use semantic_search_code instead.

• org_dependencies

  Return the bidirectional inter-repo dependency graph for the current organization.

• org_search

  FALLBACK ONLY — use org_wide_search first. Text-match search across org repos when org_wide_search returns nothing. Do NOT call as primary cross-repo search — org_wide_search has broader coverage.

• org_wide_search

  PRIMARY tool for cross-repo queries. Searches memories across ALL registered repos. Use this by default when a query spans multiple services or the answer may live in any repo. Prefer this over org_search (legacy fallback).

• record_decision

  Record an architectural decision, bug fix rationale, or 'why we did X'. Stored in episodic memory — retrievable via episodic_search in future sessions. Call when a non-obvious architectural decision is made, a bug root-cause is understood, or the user says to 'remember' something. Do NOT call for routine changes — only decisions where WHY is non-obvious. Returns: {stored: True, searchable_via: 'ep

• record_error

  Record an error Claude or the user encountered so future sessions can avoid it.

• record_user_preference

  Store an explicit user preference or query-rewrite correction.

• retrieve_memory

  Retrieve the top-k memories most similar to the query. If include_org=True, also queries sibling repositories in the same organization.

• run_serverwrite action

  Entry point called by the CLI — writes manifest then starts stdio MCP server.

• search_docs

  Search indexed documentation files (*.md, *.rst, *.txt) by semantic similarity. Use for: README explanations, architecture docs, decision logs. Do NOT use for code — use semantic_search_code instead.

• search_token

  Word-level reverse-index search.

• semantic_search_code

  Semantic vector search over indexed code symbols only (no episodic memory mixed in). Optionally filter by language: "python", "typescript", "go", etc. Do NOT call for exact string matches — use search_token or grep instead. Use for concepts and natural-language queries about what code does.

• store_memory

  Store a semantic memory with an optional source label.

• subgraph

  Return the local neighbourhood of a concept or symbol as {nodes, edges}.

• supersede_learning

  Deprecate an existing memory (by ID from store_memory conflicts list) and replace it with corrected text. Use when store_memory returns a conflict that contains incorrect or outdated information.

• who_calls

  Return every caller of a function across the indexed repo.

• Code scan102 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancelast push 2 days ago15/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Safety score

92/100

higher than 95% of 48,255 servers

Tools

35

the typical server has 7

Tools that change things

3%

typical: 0%. Fewer write tools means less an agent can break

GitHub stars

14

more than 90% of 28,688 servers

Downloads a week

30

more than 18% of 12,191 servers with a package

CogniRepo: common questions

Is CogniRepo MCP server safe?

Yes, by our scan: it is graded A (92/100). Read the CogniRepo safety report

How do I install CogniRepo?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does CogniRepo need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is CogniRepo maintained?

The last commit was 40 days ago (2026-09-25). The latest release is v1.1.1.

What can I use instead of CogniRepo?

Servers from other publishers that do the same job: Codebase Memory MCP server and Trace MCP server.

How does CogniRepo compare with other MCP servers?

safety score 92/100 (higher than 95% of 48,255 servers); tools 35 (the typical server has 7); tools that change things 3% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.