TMCRA Agent Memory

Role-aware Agent memory with cross-session recall, durable writes, and multi-Agent project scope.

Connector by reshuibuduo · GitHub account verified by the MCP Registry

IndexedApache-2.0Local (stdio)

Chalk Labs

Need help deploying TMCRA Agent Memory?

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 Desktop. Read the repository before you give any tool access to your data.

Download the bundle

MCP bundle (.mcpb): open it with Claude Desktop.

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.

About

Role-aware Agent memory with cross-session recall, durable writes, and multi-Agent project scope.

Reviews

Write a 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 and install config. Checked Oct 25, 2026.

Tools: 4 read · 2 write · 0 delete · 3 not yet classified
Secrets: None asked for
Install scripts: Not scanned yet
Runs as: Downloaded binary

Tools by what they do 9

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

Read 4 · Look things up without changing anything.

tmcra_get_job
tmcra_memory_control
tmcra_recall
tmcra_turn_prepare

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

tmcra_reconcile
tmcra_turn_commit

Not yet classified 3 · We could not tell from the name and description.

tmcra_feedback
tmcra_ingest
tmcra_wait_job

Network hosts it talks to 1

github.com · found in install command

Tools (9)

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

tmcra_feedback
Correct, ignore or restore exact memory sources after HOST CHAT confirmation. On a real user correction request first call memory_control correction_start, then clarify missing sources or replacement. Hypotheticals and quoted data do not authorize edits. This tool displays original evidence and replacement and waits for explicit acceptance; never bypass a rejected or unavailable confirmation with ingest. Reuse idempotency_key for retries; inspect effective and correction_index_status.
tmcra_get_job
Inspect a TMCRA asynchronous job.
tmcra_ingest
Persist conversation messages that have already occurred.
tmcra_memory_control
Inspect memory or apply an explicitly requested session mode, task update or recall budget. Use exact session_id; normal, recall_only and off are supported. Mark task completion only when intended.
tmcra_recall
Recall bounded, prompt-ready memory evidence for one query.
tmcra_reconcile
Retry durable pending records and report succeeded or dead-letter states.
tmcra_turn_commit
Commit the real user/assistant turn and reconcile it to terminal state.
tmcra_turn_prepare
Recall memory and return untrusted injectable context before the host answers.
tmcra_wait_job
Wait for a TMCRA job to succeed, fail, or be cancelled.

Signals

Stars: 0
Forks: 0
Open issues: 0
Last commit: Sep 5, 2026 (1 month ago)
Last release: Sep 5, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name: io.github.reshuibuduo/tmcra-mcp-server
Version: 1.0.0-rc.1
Auth: No auth
Packages: mcpb https://github.com/reshuibuduo/tmcra-mcp-server/releases/download/v1.0.0-rc.1/tmcra-mcp-server-1.0.0-rc.1.mcpb
License: Apache-2.0
Repository: github.com/reshuibuduo/tmcra-mcp-server
Website: tmcra.com
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: Official MCP Registry github-graphql

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 TMCRA Agent Memory 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.

Need help deploying TMCRA Agent Memory?

Call Get help

Cite this page

TMCRA Agent Memory MCP server. Agent Mart. https://agentmart.dev/connectors/reshuibuduo-tmcra-mcp-server (last updated 2026-10-24)