TMCRA Agent Memory MCP server
io.github.reshuibuduo/tmcra-mcp-server·v1.0.0-rc.1Role-aware Agent memory with cross-session recall, durable writes, and multi-Agent project scope.
0 stars
Reviews
Write oneNobody has reviewed TMCRA Agent Memory yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
TMCRA Agent Memory tools
No tool declarations could be read from the package source. They show once the server is installed.
Public scan report
scanner v0.1.10 · 2026-10-16 · same rubric, same numbers if you re-run it
- –Code scanpackage could not be scannedn/a
- –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 41 days ago12/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How TMCRA Agent Memory compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 80/100
- higher than 60% of 4,461 AI and agents servers
Install TMCRA Agent Memory in Claude Code, Cursor or VS Code
The registry entry has no remote endpoint or installable package.
What the publisher says
From the TMCRA Agent Memory repository's README, as published. We do not edit it. Read it on GitHub
<!-- mcp-name: io.github.reshuibuduo/tmcra-mcp-server -->
TMCRA MCP Server
TMCRA MCP Server gives MCP hosts explicit access to long-term Agent memory. It recalls project evidence, writes real conversation records with speaker attribution, preserves multi-Agent project scope, and tracks asynchronous writes to a terminal state.
中文说明
What it provides
- Cross-session project continuity. Recall bounded evidence from one stable project scope.
- Cross-tool collaboration. Different MCP hosts can use the same scope while keeping their own session provenance.
- Speaker and Agent attribution. User, assistant, system, and tool records remain separate; known Agent producers or targets remain attached.
- Explicit turn lifecycle. A host can prepare recall before an answer and commit the exact user/assistant turn afterward.
- Durable write recovery. Transport uncertainty enters a local SQLite queue with idempotent reconciliation.
- Verifiable receipts. Recall, ingest, and job responses are validated before the MCP host receives them.
- Nine MCP tools. Recall, ingest, prepare, commit, reconcile, get job, wait for job, session memory controls, and targeted feedback.
tmcramemorycontrol exposes task selection, a 12000-character default recall budget, and normal, recallonly, off modes. Pass the exact same sessionid to recall/prepare and controls. Pending older generations are discarded after a mode change; already submitted jobs remain submitted. tmcrafeedback supports ignore, correct (user-supplied replacement), and restore with a stable idempotency key. Effective feedback requires the matching backend update; check correctionindex_status separately. The visual control panel is provided by the Codex and DSH distributions. This MCP package automatically discovers the shared local installation; numeric loopback HTTP is permitted only for an explicit local identity. Hosted connections require HTTPS.
Conversational corrections now require interactive host confirmation. On an actual correction request, call tmcramemorycontrol(operation="correctionstart") before clarification or feedback to suppress automatic capture of that discussion turn. tmcrafeedback reads exact original evidence and uses MCP form elicitation to show the source, replacement and scope; only explicit acceptance submits feedback. Rejection, cancellation, expiry or an unsupported host leaves memory unchanged. Do not substitute ingestion for a rejected correction. Host lifecycle turn IDs protect the discussion from later queue replay while preserving other identified turns. A third-party host must route elicitation to its user; the server cannot guarantee that an arbitrary client will not answer automatically. Hypothetical/quoted correction language is not authorization.
Generic MCP clients decide when to call tools. Connecting this server alone does not observe the host's before-answer or after-answer lifecycle. For automatic Codex recall and capture, install the separate TMCRA Codex Memory plugin.
Install
MCPB release
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Grade history
- 2026-10-16downgradeA → Bscore 80
TMCRA Agent Memory: common questions
- Is TMCRA Agent Memory MCP server safe?
- Mostly: it is graded B (80/100). Read the TMCRA Agent Memory safety report
- Does TMCRA Agent Memory need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is TMCRA Agent Memory maintained?
- The last commit was 61 days ago (2026-09-05). The latest release is v1.0.0-rc.1.
- What can I use instead of TMCRA Agent Memory?
- Servers from other publishers that do the same job: Agent Recall MCP server, Total Agent Memory MCP server and Basic Memory MCP server.
Alternatives to TMCRA Agent Memory
Same job from other publishers: the closest match first, then the best rated.
- Agent RecallCorrection-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.not reviewedEstablishedA
- Total Agent MemoryPersistent local memory for coding agents: temporal knowledge graph, procedural and episodic recallnot reviewedEstablishedA
- Basic MemoryLocal-first knowledge management with bi-directional LLM sync via Markdown files.not reviewedWidely usedB
- PaperBananaGenerate academic diagrams and statistical plots from text using multi-agent AI.not reviewedEstablishedA
- Agent-Native ChatMinimal chat-first app with durable threads, actions, and the app-agent loopnot reviewedEstablishedA