Trust-aware agent memory with evidence-backed recall, self-inspection, and audit history.
Trust-aware agent memory with evidence-backed recall, self-inspection, and audit history. That is what the nahuali mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.
From an empty memory to evidence-backed recall: Nahuali shows what is ready to use and pauses what still needs review.
The server publishes 14 tools. What each one is for:
Self — inspection proposes work but never rewrites memory autonomouslyAxis — What it answersMEMORY — Is this memory supported enough to use?HISTORY — Do this store's recorded-history checks pass?EXTERNAL — Was this state compared with an authorized reference kept outside this store?Verdict — Meaningcertify — Available checks support use with the attached evidenceadvisory — Useful as a lead, but not ready to repeat as fact without qualificationwarn — Evidence, freshness, or store-health problems require verificationblock — The memory must not drive action until the conflict is resolvedInterface — Use it fornahuali — Shell-capable agents, scripts, sustained ingestion, inspection, recovery, receipts, and the TUIConfiguration is passed through the environment: CLAIM_ID. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.
This sits in the knowledge and memory group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Nahuali's toolset — Self, Axis, MEMORY and 11 more — is a fair guide to whether it matches your workflow. It is maintained by Arakiss; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| Self | inspection proposes work but never rewrites memory autonomously. |
| Axis | What it answers |
| MEMORY | Is this memory supported enough to use? |
| HISTORY | Do this store's recorded-history checks pass? |
| EXTERNAL | Was this state compared with an authorized reference kept outside this store? |
| Verdict | Meaning |
| certify | Available checks support use with the attached evidence. |
| advisory | Useful as a lead, but not ready to repeat as fact without qualification. |
| warn | Evidence, freshness, or store-health problems require verification. |
| block | The memory must not drive action until the conflict is resolved. |
| Interface | Use it for |
| nahuali | Shell-capable agents, scripts, sustained ingestion, inspection, recovery, receipts, and the TUI |
| nahuali-mcp | Hosts that expose MCP tools but cannot run local commands directly |
| nahuali-api | Local HTTP integrations with an OpenAPI contract |
| Variable | Description | Required |
|---|---|---|
| CLAIM_ID | Configuration value read at startup. | Optional |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.