Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Pathmark

NPM · PATHMARK · SCANNED SEP 20

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

Available components

+3 this week 87 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 31 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to hacksurvivor/pathmark). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 15 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability64
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 1657 tokens (~66/item across 25 items; 25 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management87
  • Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage73
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 19% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "delete_memory" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 25 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the Pathmark MCP server?

Pathmark runs locally as an npm package, launched with npx -y pathmark. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · pathmark

# add to Claude Code
claude mcp add hacksurvivor-pathmark -- npx -y pathmark
// .cursor/mcp.json
{
  "mcpServers": {
    "hacksurvivor-pathmark": {
      "command": "npx",
      "args": [
        "-y",
        "pathmark"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "hacksurvivor-pathmark": {
      "command": "npx",
      "args": [
        "-y",
        "pathmark"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add hacksurvivor-pathmark -- npx -y pathmark
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "hacksurvivor-pathmark": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "pathmark"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add hacksurvivor-pathmark --command npx --arg -y --arg pathmark
# ~/.hermes/config.yaml
mcp_servers:
  hacksurvivor-pathmark:
    command: "npx"
    args: ["-y", "pathmark"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "hacksurvivor-pathmark": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "pathmark"
      ]
    }
  }
}
# add to Vellum
assistant mcp add hacksurvivor-pathmark -t stdio -c npx -a -y pathmark
// mcp.json
{
  "mcpServers": {
    "hacksurvivor-pathmark": {
      "command": "npx",
      "args": [
        "-y",
        "pathmark"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

  • 8 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

  • 6 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

  • 5 Sept 26 +26
    • Malware scan: unverified → pass security
    • Known CVEs: unverified → pass security
    • Dependency health: unverified → 0.84 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed npm/pathmark@0.1.15

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo hacksurvivor/pathmark
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/hacksurvivor/pathmark/.github/workflows/publish.yml@refs/tags/v0.1.15
Rekor log index 2708438796
Predicate type https://slsa.dev/provenance/v1
Subject digest sha512:478f68d40f5dcb124bc5489a0e10c605f47de06ff71bb8db4b3e93f9637424f5b6d0b34379a862c2efd05ec1d4f63e1dc5710f6348a5fbc6be610d715

Background: How many MCP packages publish verified provenance →

Dependencies 96 packages
Packages resolved 96
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 25 exposed · ~1,657 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
approve_conclusion ~73

Approve one pending conclusion, optionally correcting its text or tags. The transition is atomic and auditable.

NameTypeReqDescription
decidedBystring
idstringyes
namespacestring
notestring
tagsarray
textstring

No output schema declared.

No examples provided.

ask_memory ~70

Ask approved conclusions first, then scoped or explicitly requested raw evidence. Returns an answer, exact provenance, and a recallId for feedback.

NameTypeReqDescription
kindstring
limitinteger
namespacestring
questionstringyes
tagsarray

No output schema declared.

No examples provided.

audit_memory ~57

Measure capture-to-recall behavior, unused records, recall age, duplicate rate, stale raw hits, and available precision evidence without changing memory.

NameTypeReqDescription
daysinteger
namespacestring
tagsarray

No output schema declared.

No examples provided.

backup_memory ~29

Create a point-in-time copy of the canonical local JSONL store.

NameTypeReqDescription
destinationstring

No output schema declared.

No examples provided.

chat ~69

Chat with Pathmark using approved conclusions first and only scoped or explicitly requested raw fallback. Returns an answer, provenance, and recallId.

NameTypeReqDescription
kindstring
limitinteger
namespacestring
questionstringyes
tagsarray

No output schema declared.

No examples provided.

compact_memory ~65

Preview or apply exact deduplication, expired-record removal, retention, and deleted-record purging. Applied runs create a backup.

NameTypeReqDescription
confirmboolean
dedupeboolean
dropDeletedboolean
retentionDaysinteger

No output schema declared.

No examples provided.

consolidate_memory ~108

Prepare a bounded unsynthesized evidence batch and, when server synthesis is configured, preview or stage evidence-backed conclusion proposals. Proposals are never auto-approved.

NameTypeReqDescription
applybooleanStage generated proposals as pending conclusions.
cursorstringContinue after the last record id from a prior bounded batch.
daysinteger
evidenceLimitinteger
maxProposalsinteger
namespacestring
tagsarray

No output schema declared.

No examples provided.

create_conclusion ~90

Propose a durable higher-signal conclusion. Approval is required by default before it can be recalled.

NameTypeReqDescription
evidenceIdsarrayRaw memory IDs supporting this conclusion. Used for provenance and consolidation coverage.
expiresAtstring
namespacestring
sourcestring
tagsarray
textstringyesConclusion text to save.

No output schema declared.

No examples provided.

delete_memory ~25

Soft-delete a saved memory or conclusion by id.

NameTypeReqDescription
idstringyes

No output schema declared.

No examples provided.

doctor_memory ~28

Report duplicate, deleted, expired, conclusion, invalid-record, and index health counts without changing data.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

export_memory ~78

Export a scoped, mergeable JSONL bundle for another Pathmark installation or trusted sync transport.

NameTypeReqDescription
destinationstringyes
encryptedbooleanEncrypt the export with PATHMARK_EXPORT_KEY.
includeDeletedboolean
kindstring
namespacestring
tagsarray

No output schema declared.

No examples provided.

get_config ~21

Show the local Pathmark Memory store location and enabled optional features.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_context ~61

Return compact local memory context for a task or question.

NameTypeReqDescription
kindstring
limitinteger
namespacestring
querystringTask or question to retrieve context for.
tagsarray

No output schema declared.

No examples provided.

get_memory_snapshot ~47

Generate a bounded USER/PROJECT/AGENT snapshot from approved canonical conclusions only.

NameTypeReqDescription
charLimitinteger
namespacestring
tagsarray

No output schema declared.

No examples provided.

list_conclusions ~35

List saved durable conclusions.

NameTypeReqDescription
limitinteger
namespacestring
tagsarray

No output schema declared.

No examples provided.

list_pending_conclusions ~56

List bounded approval-gated conclusion proposals. Pending records are never returned by normal memory search.

NameTypeReqDescription
limitinteger
namespacestring
offsetinteger
tagsarray

No output schema declared.

No examples provided.

purge_memory ~82

Preview or permanently remove matching records from the canonical store. A backup is created before an applied purge.

NameTypeReqDescription
beforestring
confirmbooleanFalse previews the purge; true applies it and creates a backup.
idstring
namespacestring
sourcestring
tagsarray

No output schema declared.

No examples provided.

rate_recall ~67

Attach explicit relevance labels to one exact Pathmark recall so audit_memory can report measured precision.

NameTypeReqDescription
irrelevantIdsarray
notestring
recallIdstringyesThe recallId returned by chat or ask_memory.
relevantIdsarray

No output schema declared.

No examples provided.

recall_memory ~176

Transparent recall for any MCP-capable harness. Use this at task start or before answering to show exactly which memories were used.

NameTypeReqDescription
idsarrayExact memory IDs from a prior Pathmark context block. Preserves the original visible-recall set.
includeRecordsbooleanInclude a second, untruncated full-record copy alongside usedMemories. Defaults to false: it duplicates data already in context/usedMemories and is unbounded in size. Set true only when full record b…
kindstring
limitinteger
namespacestring
querystringTask, repo, or question to retrieve memory for. Empty query returns recent records.
tagsarrayOptional tags to scope visible recall, such as the current workspace tag.

No output schema declared.

No examples provided.

reject_conclusion ~49

Reject one pending conclusion while retaining it in the canonical audit trail and excluding it from recall.

NameTypeReqDescription
decidedBystring
idstringyes
notestring

No output schema declared.

No examples provided.

remember ~100

Save raw searchable evidence. Durable intent should use the approval-gated conclusion workflow.

NameTypeReqDescription
expiresAtstringOptional ISO timestamp after which recall excludes this memory.
namespacestringOptional project, user, or client namespace.
sourcestringOptional source label, such as repo, thread, or tool name.
tagsarrayOptional lowercase-ish tags for later filtering.
textstringyesMemory text to save.

No output schema declared.

No examples provided.

search_memory ~58

Search saved local memories and conclusions.

NameTypeReqDescription
kindstring
limitinteger
namespacestring
querystringSearch query. Empty query returns recent records.
tagsarray

No output schema declared.

No examples provided.

session_trace ~76

Show a bounded chronological audit trail for one captured session: prompts, exact injected memory IDs, redacted tool inputs/results, and answers.

NameTypeReqDescription
includeOutputsbooleanInclude redacted bounded tool output previews. Defaults to true.
limitinteger
sessionIdstringyesExact Codex or harness session ID.

No output schema declared.

No examples provided.

supersede_memory ~72

Replace an outdated memory with a linked current record while preserving history.

NameTypeReqDescription
expiresAtstring
idstringyes
kindstring
namespacestring
sourcestring
tagsarray
textstringyes

No output schema declared.

No examples provided.

update_memory ~65

Correct an existing memory while preserving its prior versions in local history.

NameTypeReqDescription
expiresAtstring|null
idstringyes
namespacestring
sourcestring
tagsarray
textstring

No output schema declared.

No examples provided.

Common questions

What is the Pathmark MCP server?

Pathmark is an MCP server listed in the public MCP registry as io.github.hacksurvivor/pathmark. Local-first intent and provenance for Codex, Claude Code, Cursor, Gemini CLI, and MCP agents. This page covers its npm package (pathmark).

Is the Pathmark MCP server safe to use?

Pathmark scores 87 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Pathmark MCP server expose?

Pathmark exposes 25 tools: get_config, remember, create_conclusion, search_memory, get_context, and 20 more. Their descriptions and schemas cost roughly 1,657 tokens of context every time the server is loaded.

Is the Pathmark MCP server still maintained?

Pathmark is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Pathmark MCP server under?

Pathmark declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.