sovantica-engravaSAFE
Model Context Protocol server for Engrava — expose an AI agent memory database to any MCP client (Claude Desktop, Cursor, VS Code...) over stdio.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/sovantica/engrava-mcp/actions/workflows/ci.yml) [](https://pypi.org/project/engrava-mcp/) [](https://pypi.org/project/engrava-mcp/) [](https://opensource.org/licenses/MIT)
The [Model Context Protocol](https://modelcontextprotocol.io) server for [Engrava](https://github.com/sovantica/engrava) — expose an agent memory database to any MCP client (Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, ...) over stdio.
engrava-mcp is a standalone, runnable package that consumes Engrava's public API. It is the one way to run Engrava as a memory server; the engrava library itself ships no MCP code.
uv tool install engrava-mcp # recommended for daily use: a persistent install engrava-mcp # spawned by your MCP client over stdio
uvx engrava-mcp runs it without an install step, and pip install engrava-mcp works too. uvx keeps its environment in a cache. When that cache is cold, the first start waits for the download; see Optional providers for the [local] extra, where the download is largest.
Installing engrava-mcp pulls in engrava transitively, so you also get the import engrava library in the same environment.
Compatibility
engrava-mcp follows Engrava's version: `engrava-mcp X.Y.z` targets `engrava X.Y` and requires engrava >=X.Y,<X.(Y+1). This is a one-way version mirror for legibility — not a lockstep: Engrava releases on its own cadence, and engrava-mcp patch releases are independent.
The dependency rang
c04781a5e82fOBSERVED · 2026-10-13Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add engrava-mcp -- None engrava-mcp==0.7.0
Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_thought | read | async with _tool_errors(): |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- found
Findings (2)
secret = "sk-live-FAKESECRET1111111111" # noqa: S105 -- fabricated, not real
.commitlintrc.js
Gates applied: no_behavioural_pass.
c04781a5e82ffull audit observations/trust-audit/mcp-server/sovantica__engrava-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-13 | c04781a5e82f | SAFE | B | 89 | first audit |
Questions
What is the sovantica-engrava MCP server?
Model Context Protocol server for Engrava — expose an AI agent memory database to any MCP client (Claude Desktop, Cursor, VS Code...) over stdio.
What tools does sovantica-engrava expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is sovantica-engrava safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does sovantica-engrava need?
No credential environment variables were found in its source, so it appears to need none.
How does sovantica-engrava run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as engrava-mcp.
How current is this page?
The grade is for one exact copy of the source (c04781a5e82f), read on 2026-10-13. The repository is watched and re-audited when it changes.