mcpField
R
recordant

recordant

Local
mentorsentinel.aiDeveloper Tools0Updated 16w ago

About recordant

Recordant scans a target software system’s repository, changelog, and logs to produce operator briefs and track diagnoses. It is for system operators who want periodic health reviews and a decisions ledger, with an MCP console for querying and updating the same data.

Key features

  1. 01Periodic repository and log scans
  2. 02Prioritized diagnosis lists
  3. 03Operator briefs and status snapshots
  4. 04Diagnosis acknowledgment and resolution
  5. 05Accepted-risk register

Use cases

  1. 01Reviewing changes and potential breakage
  2. 02Tracking recurring open diagnoses
  3. 03Recording accepted operational risks

MCP support

Runs as an MCP server over stdio and exposes seven tools for briefs, status, diagnosis lists, acknowledgment, risk acceptance, and resolution.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"recordant-recordant": {
"command": "uvx",
"args": [
"recordant"
],
"env": {
"RECORDANT_LICENSE_KEY": "<RECORDANT_LICENSE_KEY>"
}
}
}
}
Run commanduvx recordant
Environment variables to set
RECORDANT_LICENSE_KEYSecretYour Recordant license key. Auth-by-default -- the console will not start without a valid key. Get one at https://mentorsentinel.ai/markets-ai-governance.html.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypirecordant0.2.2

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Recordant

Recordant is a patent-pending diagnostic + decisions-ledger engine for any host software system. Point it at a target's repo, changelog, and logs, and it runs a periodic scan that produces an operator brief: what changed, what looks broken, what was fixed, and a prioritized diagnosis list — plus a chat-native MCP console over the same data.

Bring your own LLM (Anthropic, OpenAI, or Gemini — your key, your usage, your bill). Recordant makes no provider assumption.

15-minute install and first brief

  1. Install the package and your LLM provider's SDK (only the one you use):

    pip install "recordant[anthropic]"     # or [openai], [gemini], or [all]
    
  2. Copy recordant.example.toml to recordant.toml and set:

    • repo_root — the target repo to diagnose
    • changelog_path — usually CHANGELOG.md (falls back to git log if absent)
    • log_globs — which log files to health-scan
    • [llm] — your provider, model, and api_key_env (the name of the environment variable holding your key — never the key itself)
  3. Export your key and run one cycle:

    export RECORDANT_LLM_KEY=sk-...
    recordant --config recordant.toml
    

    The brief path prints to stdout. The brief, snapshot, and (optional) decisions ledger are written under your configured output_dir.

  4. Schedule it (cron / systemd timer / your own scheduler) at the schedule_seconds cadence in your config.

That's the whole loop. See ENGINE.md for the adapter architecture, config reference, and known limitations.

MCP console

Recordant also runs as an MCP server exposing 7 tools over stdio, for use from a chat-native MCP client:

ToolPurpose
recordant_briefLatest delta brief since the prior cycle
recordant_statusCurrent status snapshot (health, cadence, active book)
recordant_digestOpen items, Accepted-Risk Register, fixes shipped, deadlines
recordant_open_itemsEvery open diagnosis with age, recurrence, evidence
recordant_acknowledgeAcknowledge a diagnosis (P0 items cannot be acknowledged)
recordant_accept_riskPin a diagnosis in the Accepted-Risk Register
recordant_resolveAssert a diagnosis is resolved (audited against the changelog)

Token-auth is on by default — there is no anonymous mode. The server requires a valid RECORDANT_LICENSE_KEY and verifies it against the license service at startup before registering a single tool; it will not run unlicensed, even briefly. A short offline-grace window covers a transient network failure to the license service, but an explicitly invalid or expired key is refused immediately.

export RECORDANT_LICENSE_KEY=rk-...
recordant-mcp --config recordant.toml

Add it to your MCP client's config (Claude Desktop, Claude Code, etc.):

{
  "mcpServers": {
    "recordant": {
      "command": "recordant-mcp",
      "args": ["--config", "/absolute/path/to/recordant.toml"],
      "env": { "RECORDANT_LICENSE_KEY": "rk-..." }
    }
  }
}

Licensing and pricing

Recordant is licensed software, not open source (see LICENSE). Get a key and see current pricing at https://mentorsentinel.ai/markets-ai-governance.html.

Docker

Recordant ships as a compiled image -- there is no engine source to build from, so docker build is not part of a customer workflow. Pull the licensed image (published per BUILD-RELEASE.md) and run it:

docker pull recordant/recordant:<version>
docker run -v $PWD/recordant.toml:/app/recordant.toml:ro \
           -v $PWD/target-repo:/app/target-repo:ro \
           -e RECORDANT_LLM_KEY \
           recordant/recordant:<version> --config recordant.toml

The image is signed (cosign) and ships with an SBOM (syft) so you can audit what it does -- dependencies, egress -- without needing readable engine source; see BUILD-RELEASE.md for verification commands.

See docker-compose.example.yml for a compose-based setup, including the MCP console service.

Support

Found a bug or have a feature request? Open an issue — see .github/ISSUE_TEMPLATE/. For licensing or account questions, use the pricing page above.

Patents

Recordant's inference loop and decisions-ledger lifecycle are patent-pending (U.S. application numbers available on request). "Patent-pending" reflects filed, unexamined provisional applications — no patent has issued.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.