← Index

Midas

io.github.vornicx/midasv0.0.1AI & LLMs

Local-first, source-traceable agent memory — no LLM at ingest, fully offline

In-path gate · all MCP tools

Using Midas in Claude, Cursor, Gemini CLI, Cline, or Zed?

MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).

Install the mcpindex gate (one command)

Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less

uv tool install mcpindex-gate && mcpindex-config-wire
Trust verdict · v1 advisory · method
NOT YET SCREENEDno verdict on file

Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.

Own this server? Screen its description →

That verdict was true at screening time (snapshot 2026-07-23).

Contracts can change after screening, with no version bump. The gate pins Midas’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.

See your first HOLD in 2 minutes →

Related: how to trust an MCP server · screen before install · silent contract drift

Environment variables
MIDAS_MCP_DB

Path to a SQLite file to persist memory across restarts (default: in-memory)

MIDAS_MCP_EMBEDDER

Embedding backend: 'local' (bge ONNX, offline) or 'hashing' (default: local)

MIDAS_MCP_MAX_RECORDS

Cap the store; above it the lowest-value memories are auto-forgotten (no LLM)

MIDAS_MCP_MIN_IMPORTANCE

Relevance floor 1-5 for auto-capture; turns scoring below it are skipped

MCP quality score · maturity, not trust · methodology
freshness
24
completeness
15
installability
25
documentation
15
stability
5
Alternatives in AI & LLMs