Menhir
UnclaimedEvidence-backed graph memory and code-impact analysis for coding agents, served over MCP.
Set up this server
More in AI & ML
Browse the full directoryUnclaimed listing
Is this your MCP server?
This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.
Claim this serverSecurity profile
Claimed and verified servers get a weekly static scan that shows what the code can reach: external services, environment variables, shell commands, agent configuration folders, plus any dependencies with known advisories. Claim this listing to get one. How the security profile works
29 of 29 tools
Documented tools (29)
From project documentation. A server handshake does not verify each tool’s description or behavior.
add_candidate
Stage low-trust context for human review without making it recallable
add_memory
Queue a memory for enrichment
add_memory_and_track
Queue a memory and stream processing progress
add_todo
Create a todo with an optional normalized code location
build_context
Assemble context within a token budget
delete_memory
Delete a memory under operator control
flag_memory
Protect a memory from normal lifecycle decay
get_artifact
Read one artifact with its current metadata and Git-backed content
get_enrichment_status
Inspect one episode's processing state
get_episode_trace
Read queue and telemetry history for an episode
get_memory_stats
Summarize latency, failures, and queue depth
get_provenance
Expand a result into source episodes, evidence, and code anchors
ingest_document
Ingest a document as memory episodes
ingest_project
Index a repository's structure
link_artifacts
Record a typed reviews, implements, or informs relationship
list_artifacts
Find plans, reviews, investigations, reports, and handoffs by type or status
list_conflicts
List grouped contradictions
promote_memory
Mark persistent memory as operator-verified ground truth
query_structure
Query code context, blast radius, affected tests, symbols, endpoints, dependencies, and cross-project references
rate_recall
Record explicit retrieval feedback
read_flagged_memories
Read memories selected for bootstrap
recall_context_memories
Retrieve recent and relevant startup context
recall_memories
Search and rerank memories, with optional file context
resolve_conflict
Keep both memories, replace one, or discard the new one
run_llm_conflict_review
Ask the configured LLM to review unresolved conflicts
scan_for_conflicts
Scan for similarity-based conflict candidates
supersede_artifact
Replace an artifact while updating status and relationship atomically
transition_artifact
Apply a legal status transition for that artifact type
watch_enrichment
Monitor enrichment changes
Tool change history
FAQ
Questions about Menhir MCP Server
- How do I connect Menhir MCP Server to Claude?
- The project does not publish a launch command that MCPVault could verify. Open the repository linked on this page for its install steps; the listing names Claude Code as compatible clients.
- Is Menhir MCP Server free?
- The listed licence is Apache-2.0. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.
- What can Menhir MCP Server do?
- Menhir MCP Server documents 29 tools to the agent, including add_candidate, add_memory, add_memory_and_track. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.