Pathmark
UnclaimedPathmark — local-first memory for Codex, Claude Code, Gemini CLI, Cursor and MCP agents, created by B2B AI specialist Sergey Moloman.
Install
pathmarkSet 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
25 of 25 tools
Documented tools (25)
From project documentation. A server handshake does not verify each tool’s description or behavior.
approve_conclusion
Atomically approve a proposal, optionally correcting text/tags and recording the reviewer.
ask_memory
Return an approved-conclusion answer or scoped raw context, exact provenance, and a recall ID for feedback.
audit_memory
Measure capture-to-recall behavior, unused records, recall age, duplicates, stale raw hits, and whether precision labels exist.
backup_memory
Create a point-in-time canonical JSONL backup.
chat
Chat-compatible alias for askmemory, including multi-intent conclusion retrieval and explicit abstention.
compact_memory
Preview or apply deduplication, retention, and physical cleanup with an automatic backup.
consolidate_memory
Review a bounded unsynthesized evidence batch and optionally stage evidence-backed proposals. Nothing is auto-approved.
create_conclusion
Propose a higher-signal durable conclusion or preference. Approval is required by default before recall.
delete_memory
Soft-delete a memory or conclusion by id.
doctor_memory
Report duplicates, deleted/expired records, conclusions, and index health.
export_memory
Export a scoped mergeable JSONL bundle, optionally encrypted.
get_config
Show local store configuration.
get_context
Return compact context for a task or question.
get_memory_snapshot
Generate a bounded USER/PROJECT/AGENT snapshot from approved canonical conclusions.
list_conclusions
List approved saved conclusions.
list_pending_conclusions
Review bounded, paginated pending conclusion proposals.
purge_memory
Preview or apply permanent deletion by id, namespace, tags, source, or date.
rate_recall
Label exact IDs from a chat / askmemory recall as relevant or irrelevant so audit precision is measured.
recall_memory
Transparent recall: returns context plus the exact memory IDs, timestamps, sources, matches, tags, and previews used. Accepts optional tags, exact ids, and compact includeRecords: false output.
reject_conclusion
Retain a rejected proposal in the audit trail while permanently excluding it from recall.
remember
Save raw searchable evidence. Raw evidence is not treated as durable approved intent.
search_memory
Search memories and conclusions.
session_trace
Return a bounded chronological audit trail for one session: prompts, exact injected memory IDs, redacted tool inputs/results, and answers.
supersede_memory
Replace an outdated record with a linked current record.
update_memory
Correct a record while preserving prior versions.
Tool change history
FAQ
Questions about Pathmark MCP Server
- How do I connect Pathmark MCP Server to Claude?
- The listing records `pathmark` as its setup step. Run it, then follow the repository's instructions for the client configuration; the listing names Claude Desktop, Claude Code, Cursor as compatible clients.
- Is Pathmark MCP Server free?
- The listed licence is MIT. 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 Pathmark MCP Server do?
- Pathmark MCP Server documents 25 tools to the agent, including approve_conclusion, ask_memory, audit_memory. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.