Pathmark MCP server

by hacksurvivor·io.github.hacksurvivor/pathmark·v0.1.17·3 stars

No reviews yet

Local-first intent and provenance for Codex, Claude Code, Cursor, Gemini CLI, and MCP agents.

A92/100grade A

Write a review Install

What users say

No reviews yet

Be the first

Safety scan

A92/100

full report

Adoption

Growing

3 stars134 downloads/wk

Reviews

Write one

Nobody has reviewed Pathmark yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Pathmark tools (25, 4 write)

write = sends, deletes, buys or posts

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

approve_conclusion
Approve one pending conclusion, optionally correcting its text or tags. The transition is atomic and auditable.
ask_memory
Ask approved conclusions first, then scoped or explicitly requested raw evidence. Returns an answer, exact provenance, and a recallId for feedback.
audit_memory
Measure capture-to-recall behavior, unused records, recall age, duplicate rate, stale raw hits, and available precision evidence without changing memory.
backup_memorywrite action
Create a point-in-time copy of the canonical local JSONL store.
chat
Chat with Pathmark using approved conclusions first and only scoped or explicitly requested raw fallback. Returns an answer, provenance, and recallId.
compact_memory
Preview or apply exact deduplication, expired-record removal, retention, and deleted-record purging. Applied runs create a backup.
consolidate_memory
Prepare a bounded unsynthesized evidence batch and, when server synthesis is configured, preview or stage evidence-backed conclusion proposals. Proposals are never auto-approved.
create_conclusionwrite action
Propose a durable higher-signal conclusion. Approval is required by default before it can be recalled.
delete_memorywrite action
Soft-delete a saved memory or conclusion by id.
doctor_memory
Report duplicate, deleted, expired, conclusion, invalid-record, and index health counts without changing data.
export_memory
Export a scoped, mergeable JSONL bundle for another Pathmark installation or trusted sync transport.
get_config
Show the local Pathmark Memory store location and enabled optional features.
get_context
Return compact local memory context for a task or question.
get_memory_snapshot
Generate a bounded USER/PROJECT/AGENT snapshot from approved canonical conclusions only.
list_conclusions
List saved durable conclusions.
list_pending_conclusions
List bounded approval-gated conclusion proposals. Pending records are never returned by normal memory search.
purge_memory
Preview or permanently remove matching records from the canonical store. A backup is created before an applied purge.
rate_recall
Attach explicit relevance labels to one exact Pathmark recall so audit_memory can report measured precision.
recall_memory
Transparent recall for any MCP-capable harness. Use this at task start or before answering to show exactly which memories were used.
reject_conclusion
Reject one pending conclusion while retaining it in the canonical audit trail and excluding it from recall.
remember
Save raw searchable evidence. Durable intent should use the approval-gated conclusion workflow.
search_memory
Search saved local memories and conclusions.
session_trace
Show a bounded chronological audit trail for one captured session: prompts, exact injected memory IDs, redacted tool inputs/results, and answers.
supersede_memory
Replace an outdated memory with a linked current record while preserving history.
update_memorywrite action
Correct an existing memory while preserving its prior versions in local history.

Public scan report

scanner v0.1.10 · 2026-10-16 · same rubric, same numbers if you re-run it

no findings

Code scan75 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

Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

How Pathmark compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score: 92/100; higher than 93% of 48,243 servers
Tools: 25; the typical server has 7
Tools that change things: 16%; typical: 0%. Fewer write tools means less an agent can break
GitHub stars: 3; more than 80% of 28,706 servers
Downloads a week: 134; more than 69% of 12,306 servers with a package

What its tools let an agent do: 19 read · 1 create · 3 change · 2 delete

Release history: 3 versions in the registry since 2026-09-04, latest 2026-09-28, typically one every 20 days.

Install Pathmark in Claude Code, Cursor or VS Code

Runs npx -y pathmark on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add pathmark -- npx -y pathmark

Add to Cursor

What the publisher says

From the Pathmark repository's README, as published. We do not edit it. Read it on GitHub

Pathmark

Carry intent across agents without turning stale code facts into hidden memory.

What's New — v0.1.15

Pathmark v0.1.15 keeps proactive memory useful without making the conversation noisy:

relevant memory is still injected automatically before Codex answers;
raw recall_memory tool output is now hidden by default, keeping the chat focused on the answer instead of memory plumbing;
PATHMARKCODEXVISIBLE_RECALL=on restores the explicit recall trace whenever you want to audit which records were used;
vulnerable transitive fast-uri and qs versions are replaced by patched releases in the published dependency lock.

See the v0.1.15 release notes or the complete changelog. The npm badge above always shows the currently published version.

Pathmark gives Codex, Claude Code, opencode, Gemini CLI, Cursor, and any MCP-capable harness one local intent and provenance layer. Save decisions, constraints, preferences, and approved conclusions once. Use them from the next agent without pasting a recap.

Code remembers implementation. Pathmark remembers intent. Repository code, architecture, tests, CI, and intentional agent instructions remain authoritative for how the software works. Raw sessions are searchable evidence, not automatically trusted truth.

Your context stays on disk at ~/.pathmark/memory/memory.jsonl. You do not need an account, hosted database, API key, or vendor backend to start.

OpenAI Build Week 2026

Pathmark is a Developer Tools submission for OpenAI Build Week 2026. The project existed before the challenge, so the submission is deliberately scoped to the meaningful extension built after the submission period opened on July 13, 2026.

During the eligible period, Codex with GPT-5.6 helped audit and extend Pathmark from a working local memory layer into safer long-running developer infrastructure:

fixed a reproduced multi-process SQLite index race;
added revision history, superseding, expiration, retention, diagnostics, backup, compaction, and preview-first hard purge;
added namespace-scoped reads and writes plus default secret redaction;
added scoped import/export, optional AES-256-GCM portable exports, local hybrid reranking, and portable harness ingestion;
hardened CI and npm delivery with required CodeQL and dependency review, immutable Action pins, protected tags, OpenSSF analysis, and SLSA provenance.

The primary Codex session for this work is 019f5fc3-d7e6-7b41-8a30-d161c90b98fb. The qualifying release range is v0.1.6 through v0.1.7; the pre-challenge baseline is commit 4c0e87dfdbd2ba4c643abd8b887cc228bdb08b73.

See the Build Week implementation record for the before/after boundary, commit evidence, Codex collaboration details, and a fast judge test.

Why Pathmark

You do not work in one tool. You ask Codex to patch, Claude Code to review, opencode to clean up, and Gemini CLI to challenge the plan. Each tool starts cold unless you carry the context across.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Pathmark: common questions

Is Pathmark MCP server safe?: Yes, by our scan: it is graded A (92/100). Read the Pathmark safety report
How do I install Pathmark?: It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Pathmark need an API key?: Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Pathmark maintained?: The last commit was 22 days ago (2026-10-14). The latest release is v0.1.17.
How does Pathmark compare with other MCP servers?: safety score 92/100 (higher than 93% of 48,243 servers); tools 25 (the typical server has 7); tools that change things 16% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.