Skip to content
Agentmart
Submit a tool

Mneme Decision MCP

Local MCP server for architectural decisions, traceability, and non-authoritative proposals.

Connector by MnemeHQ · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 28
Write a review

Chalk Labs

Need help deploying Mneme Decision MCP?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/mnemehq-mneme

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Local MCP server for architectural decisions, traceability, and non-authoritative proposals.

Use cases: documentation, code-review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools
4 read · 2 write · 0 delete
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Tools by what they do 6

Read from the source code; the running server may list different tools.

Read 4 · Look things up without changing anything.

  • decision.applicable_to
  • decision.get
  • decision.search
  • decision.trace

Write 2 · Create, change, send or run things.

  • decision.propose
  • decision.propose_batch

Network hosts it talks to 17

  • api.github.com · found in code
  • blackhole.invalid · found in code
  • chatgpt.com · found in code
  • errors.pydantic.dev · found in code
  • github.com · found in code
  • glama.ai · found in code
  • googleapis.com · found in code
  • googletagmanager.com · found in code
  • mcp-index.tensorblock.co · found in code
  • mcphq.ai · found in code
  • mcpnav.dev · found in code
  • mcprepository.com · found in code
  • mcpservers.org · found in code
  • mneme-audit-api-842519822929.us-central1.run.app · found in code
  • mnemehq.com · found in code
  • raw.githubusercontent.com · found in code
  • roninforge.org · found in code

Files it touches

  • ~/.claude
  • C:\\Users\\hi\\.claude\\projects\\C--Users-hi-AppData-Local-Temp-mneme-confirmatory-mechanism-isolation-xttvp9lt-workspace\\memory\\adr_auth_cookies.md
  • C:\\Users\\hi\\.claude\\projects\\C--Users-hi-AppData-Local-Temp-mneme-confirmatory-mechanism-isolation-xttvp9lt-workspace\\memory\\adr_storage_sqlite.md
  • C:\\Users\\hi\\.claude\\projects\\C--Users-hi-AppData-Local-Temp-mneme-confirmatory-mechanism-isolation-xttvp9lt-workspace\\memory\\MEMORY.md
  • /home/runner/work/mneme/mneme/mneme/__init__.py
  • /root/production_lock_review
  • Your home directory (~)
  • C:\\\\Users\\\\hi\\\\AppData\\\\Local\\\\Temp\\\\mneme-confirmatory-mechanism_isolation-g11h9rxo\\\\workspace\\\\src\\\\sessions.py
  • C:\\dev\\mneme\\.worktrees\\feat-bench-phase1\\mneme\\__init__.py
  • C:\\dev\\mneme\\.worktrees\\feat-cm01-s1a1-e0-local-executor\\validation\\cm01\\s1a-local\\m1\\fixture\\canonical\\project_memory.json
  • C:\\dev\\mneme\\.worktrees\\feat-cm01-s1a1-e0-local-executor\\validation\\cm01\\s1a-local\\m1\\fixture\\pre_migration.json
  • C:\\dev\\mneme\\.worktrees\\feat-cm01-s1a1-e0-local-executor\\validation\\cm01\\s1a-local\\m4\\fixture\\canonical\\project_memory.json
  • C:\\dev\\mneme\\.worktrees\\feat-cm01-s1a1-e0-local-executor\\validation\\cm01\\s1a-local\\m4\\fixture\\pre_migration.json
  • C:\\dev\\mneme\\.worktrees\\feat-cm01-s1a1-e0-local-executor\\validation\\cm01\\s1a-local\\m8\\fixture\\sectionless.json
  • C:\\dev\\mneme\\.worktrees\\feat-codex-cli-enforcement\\.venv
  • C:\\dev\\mneme\\.worktrees\\feat-codex-cli-enforcement\\validation\\codex-cli\\probe\\sandbox\\repo
  • C:\\dev\\mneme\\.worktrees\\feat-codex-cli-enforcement\\validation\\codex-cli\\probe\\sandbox\\repo\\setcontent.txt\
  • C:\\dev\\mneme\\.worktrees\\feat-hook-latency-benchmark
  • C:\\dev\\mneme\\.worktrees\\feat-hook-latency-benchmark\\mneme\\__init__.py
  • C:\\dev\\mneme\\.worktrees\\feat-langchain-agent-middleware\\validation\\langgraph\\evidence\\runs\\20260825T162444Z-m0\\mneme-lg-m0-sdk4a38w\\s1\\scripts\\slack_outreach.py
  • C:\\dev\\mneme\\.worktrees\\feat-langchain-agent-middleware\\validation\\langgraph\\evidence\\runs\\20260825T162444Z-m0\\mneme-lg-m0-sdk4a38w\\s4-allow\\scripts\\slack_outreach.py
  • C:\\dev\\mneme\\.worktrees\\feat-langchain-agent-middleware\\validation\\langgraph\\evidence\\runs\\20260825T162444Z-m0\\mneme-lg-m0-sdk4a38w\\s6\\scripts\\slack_outreach.py
  • C:\\dev\\mneme\\.worktrees\\fix-bench-bytecode
  • C:\\dev\\mneme\\.worktrees\\fix-bench-bytecode\\mneme\\__init__.py
  • C:\\dev\\mneme\\.worktrees\\ox-compaction\\validation\\ox-compaction\\runs\\preflight-A-02\\workspace
  • C:\\dev\\mneme\\.worktrees\\ox-compaction\\validation\\ox-compaction\\runs\\preflight-B-02\\workspace
  • C:\\dev\\mneme\\.worktrees\\ox-compaction\\validation\\ox-compaction\\runs\\preflight-B-03\\workspace
  • C:\\dev\\mneme\\.worktrees\\ox-compaction\\validation\\ox-compaction\\runs\\run-01-a1\\workspace
  • C:\\dev\\mneme\\.worktrees\\ox-compaction\\validation\\ox-compaction\\runs\\run-02-b1\\workspace
  • C:\\dev\\mneme\\.worktrees\\ox-compaction\\validation\\ox-compaction\\runs\\run-03-b2\\workspace
  • C:\\dev\\mneme\\.worktrees\\ox-compaction\\validation\\ox-compaction\\runs\\run-05-b3\\workspace
  • C:\\dev\\mneme\\.worktrees\\ox-compaction\\validation\\ox-compaction\\runs\\run-06-a2\\workspace
  • C:\\dev\\mneme\\.worktrees\\ox-compaction\\validation\\ox-compaction\\runs\\run-07-a3\\workspace
  • C:\\dev\\mneme\\.worktrees\\ox-compaction\\validation\\ox-compaction\\runs\\run-08-b4\\workspace
  • C:\\dev\\mneme\\.worktrees\\refactor-cli-lazy-imports
  • C:\\dev\\mneme\\.worktrees\\refactor-cli-lazy-imports\\mneme\\__init__.py
  • C:\\Users\\hi\\.codex\\.codex-global-state.json
  • C:\\Users\\hi\\.codex\\sessions\\2026\\08\\24\\rollout-2026-08-24T05-07-27-01a0333d-3ffd-75c0-a38e-315c852fb7d5.jsonl
  • C:\\Users\\hi\\.codex\\sessions\\2026\\08\\24\\rollout-2026-08-24T05-07-42-01a0333d-7a5b-72c3-afab-93db5c746574.jsonl
  • C:\\Users\\hi\\.codex\\sessions\\2026\\08\\24\\rollout-2026-08-24T05-18-01-01a03346-ee6b-7c81-87e0-cbeab8812b69.jsonl

Tools (6)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • decision.applicable_toGet retrieval/context applicability

    Return proposals and canonical decisions whose scope hints or context scope overlap the supplied context/paths. This is retrieval/context applicability only: proposal scope hints are NOT typed-rule applicability (ADR-020) and paths are never glob-evaluated. Read only: this tool never mutates any state and returns no rules or enforcement data. When both inputs are omitted or empty, both match lists are empty.

  • decision.getGet a proposal or canonical decision

    Read one record by stable id. Returns record_type 'proposal', 'canonical_decision', or 'not_found'. Read only: this tool never mutates any state. Use decision.search when you do not already have a stable id.

  • decision.proposePropose a decision (non-authoritative)

    Submit one candidate architectural decision. The proposal enters the Mneme decision index as a non-authoritative proposal with status 'proposed'. This grants NO authority: the proposal is never enforceable and can only become canonical through separate Mneme human authority (D2C), which this MCP does not expose. Repeated identical source/version/content submissions are idempotent. Use decision.propose_batch when submitting multiple candidates.

  • decision.propose_batchPropose decisions in batch (non-authoritative)

    Submit multiple candidate architectural decisions from one producer output. Each candidate receives its own independent proposal identity and enters as a non-authoritative proposal with status 'proposed'. There are no batch acceptance semantics: batch submission grants NO authority, and every proposal remains independently reviewable. Use decision.propose for a single candidate.

  • decision.searchSearch proposals and canonical decisions

    Deterministic text/exact-metadata search. Proposals (lifecycle proposed/accepted/rejected) and canonical decisions (lifecycle active/superseded/deprecated/inactive) are returned in separate lists and never merged. Read only: this tool never mutates any state. Search rank has no enforcement meaning. Use decision.get when you already have a stable id. Within each record domain, all applicable filters combine with AND semantics; proposal-only filters do not exclude canonical results, and vice versa.

  • decision.traceTrace decision lineage

    Return the deterministic lineage actually known for a proposal id or canonical decision id. The result_type is explicit (proposal_trace / canonical_trace / trace_not_found); unresolved ids stay type-unknown. Read only: this tool never mutates any state. Canonical rule-lineage integrity failures fail closed as protocol errors and are never returned as partial traces. Use decision.get for the record alone; use decision.trace when you need provenance, acceptance, rule, or declared-evidence lineage.

Signals

Stars
28
Forks
4
Open issues
39
Contributors
4
Weekly downloads
687
Last commit
Oct 24, 2026 (7 days ago)
Last release
Oct 7, 2026 (23 days ago)
Last package publish
Oct 7, 2026 (23 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name
io.github.MnemeHQ/mneme
Version
0.10.0
Auth
No auth
Packages
pypi mneme-hq
License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get Mneme Decision MCP running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying Mneme Decision MCP?

CallGet help
Cite this page

Mneme Decision MCP. Agent Mart. https://agentmart.dev/connectors/mnemehq-mneme (last updated 2026-10-24)