Back to Browse

Gmi Security MCP Server

SecurityLow Risk10.0MCP RegistryLocal
Free

Server data from the Official MCP Registry

Triage semgrep findings with GMI Inference, with cost shown before every run.

About

Triage semgrep findings with GMI Inference, with cost shown before every run.

Security Report

10.0
Low Risk10.0Low Risk

Valid MCP server (2 strong, 2 medium validity signals). No known CVEs in dependencies. Imported from the Official MCP Registry. 1 finding(s) downgraded by scanner intelligence.

6 files analyzed · 1 issue found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

file_system

Check that this permission is expected for this type of plugin.

database

Check that this permission is expected for this type of plugin.

What You'll Need

Set these up before or after installing:

GMI Inference API keyRequired

Environment variable: GMI_API_KEY

How to Install

Add this to your MCP configuration file:

{
  "mcpServers": {
    "gmi-security-mcp": {
      "command": "uvx",
      "args": [
        "gmi-security-mcp==0.5.11"
      ],
      "env": {
        "GMI_API_KEY": "your-gmi-api-key-here"
      }
    }
  }
}

Some servers take additional arguments. See the repository for details.

Documentation

View on GitHub

From the project's GitHub README.

gmi-security-mcp

A security MCP server for coding agents, backed by GMI Inference. Your agent triages semgrep findings, scans repos, checks lockfiles against OSV, and verifies findings with a runnable PoC, all inside the editor, with the cost shown before every run. GMI Security MCP server

PyPI: https://pypi.org/project/gmi-security-mcp/ — MCP Registry: https://registry.modelcontextprotocol.io/v0/servers?search=gmi-security-mcp — Repo: https://github.com/Jayanng/gmi-security-mcp

Install

Requires Python 3.13 or later and a GMI Inference API key. No GitHub token is needed for local repos.

pip install gmi-security-mcp
export GMI_API_KEY="your-gmi-key"
gmi-security-mcp --list-tools

That prints the 15 tool names. Run the server as a stdio MCP server with gmi-security-mcp, or run the 12 built-in examples with mcp-test, which spends under $0.02 with the default model. pipx install gmi-security-mcp works the same way, in an isolated venv.

Quick start

Add the server to Claude Code with claude mcp add gmi-security-mcp -e GMI_API_KEY="your-gmi-key" -- gmi-security-mcp, or drop this in .mcp.json:

{
  "mcpServers": {
    "gmi-security-mcp": {
      "command": "gmi-security-mcp",
      "env": { "GMI_API_KEY": "your-gmi-key" }
    }
  }
}

Config copies for Claude Code, Codex, and Cursor are in install/. Editor test status: Claude Code and Codex are tested for registration and tools/list only, Cursor is not tested end-to-end. See TUTORIAL.md section 2.

Tools

ToolWhat it does
triage_semgrep_findingTriage one finding. One validated verdict: real or false positive, severity, confidence, reason, fix.
repo_scanScan a repo with semgrep and osv-scanner, then two-stage triage of each finding. Returns a JSON report.
check_osv_advisoryCheck one lockfile against OSV. No GMI call.
explain_cveExplain a CVE, GHSA, or OSV id from its advisory, with citations.
draft_private_disclosureDraft a private disclosure from a confirmed real finding. Drafts only, never sent.
estimate_costEstimate a run before it spends anything. No GMI call, no spend.
verify_findingProve a finding with a deterministic oracle and a runnable PoC.
list_findingsList stored findings, summaries only, no code.
get_findingOne stored finding in full: code, evidence, verdict history, verification results.
update_findingUpdate a stored finding. A reason is required.
mark_fpMark a finding false positive, with a reason.
mark_confirmedMark a finding confirmed, with a reason. Only with a reproduced verification.
list_rulesList the custom semgrep rules pack: 8 rules, all enabled by default.
scope_enableEnable a scope policy for one repo from a scope file.
scope_disableDisable the scope policy for one repo.

Cost and safety

Estimate before every run. The default cap is $1.00 per tool call and cannot go above $5.00. A single finding typically costs $0.0001 to $0.001 with Gemini 3.5 Flash Lite. A model verdict alone never confirms a finding: only a deterministic oracle reproducing it does, and a generated PoC never runs on your host until you review and confirm it. Secrets are redacted before anything is sent to GMI, and the key comes from GMI_API_KEY only, never from a file. Drafts are never sent, opened as a PR, forked, pushed, or emailed by this server.

Docs

  • TUTORIAL.md: full worked tutorial, every command with real output, plus the reference appendix with tool details, cost records, limitations, and repo structure.
  • CHANGELOG.md: version history, including what is new in 0.5.8.
  • DECISIONS.md: design decisions and the audit record behind them.
  • DATA_SOURCES.md: where the model pricing comes from and when it was last re-checked live.

Development

python3 -m venv .venv
.venv/bin/pip install -e ".[dev]"
python3 -m pytest tests/ -q

Unit tests need no key and no network. 328 tests pass. Live tests are separate and capped: $1.00 per full run, $5.00 total for the whole build.

License

MIT. See LICENSE.

Reviews

No reviews yet

Be the first to review this server!