# gmi-security-mcp (pypi · gmi-security-mcp)

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

- Trust score: 65/100 (medium)
- Change this week: −11
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- pypi · `gmi-security-mcp`: 65/100 (this document), [markdown](https://verifymcp.io/servers/jayanng-gmi-security-mcp/gmi-security-mcp.md), [page](https://verifymcp.io/servers/jayanng-gmi-security-mcp/gmi-security-mcp)

## Channel facts

- Registry: `pypi`
- Package: `gmi-security-mcp`
- Version: `0.5.11`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it.
  - 1 of 29 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to Jayanng/gmi-security-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 8 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 55/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2321 tokens (~154/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the gmi-security-mcp server?

gmi-security-mcp runs locally as a PyPI package, launched with uvx gmi-security-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add jayanng-gmi-security-mcp -- uvx gmi-security-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "jayanng-gmi-security-mcp": {
      "command": "uvx",
      "args": [
        "gmi-security-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "jayanng-gmi-security-mcp": {
      "command": "uvx",
      "args": [
        "gmi-security-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add jayanng-gmi-security-mcp -- uvx gmi-security-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "jayanng-gmi-security-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "gmi-security-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add jayanng-gmi-security-mcp --command uvx --arg gmi-security-mcp
```

### Hermes

```yaml
mcp_servers:
  jayanng-gmi-security-mcp:
    command: "uvx"
    args: ["gmi-security-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "jayanng-gmi-security-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "gmi-security-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add jayanng-gmi-security-mcp -t stdio -c uvx -a gmi-security-mcp
```

### Other

```json
{
  "mcpServers": {
    "jayanng-gmi-security-mcp": {
      "command": "uvx",
      "args": [
        "gmi-security-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 65, −14)

- [security regression] Malware scan: pass → unverified

### 2026-11-20 (score 79, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-19 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-15 (score 62, −14)

- [security regression] Malware scan: pass → unverified

### 2026-11-14 (score 76, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-13 (score 61, −14)

- [security regression] Malware scan: pass → unverified

### 2026-11-12 (score 75, +15)

- [security improvement] Malware scan: unverified → pass
- [functional improvement] Stability: unverified → 0.03
- [functional] Package version: 0.5.8 → 0.5.11
- [functional] Package version: 0.5.8 → 0.5.10

## MCP tools (15)

### `triage_semgrep_finding` (~219 tokens)

Triage one semgrep or scanner finding with GMI Inference.

Returns one validated finding as JSON: verdict, severity,
confidence, reason, fix, stage used, latency, tokens, cost, and
the estimate made before the call. An unparsed reply returns
verdict null and unparsed true. It never returns clean. The
verdict is stored in the findings store (per-user
\~/.gmi-security-mcp/findings.db by default) and the result
carries finding_id. An explicit db_path is allowed, with a
warning that the caller is responsible for not committing it.

Input parameters:

- `check`
- `code` (string, required)
- `db_path`
- `file`
- `finding` (string, required)
- `line`
- `max_tokens` (integer)
- `spend_cap_usd` (number)
- `stage1_model`
- `stage2_model`
- `threshold` (number)
- `two_stage` (boolean)

Output parameters:

- `result` (string)

### `estimate_cost` (~88 tokens)

Estimate the cost of a run with no API call and no spend.

Returns typical and maximum cost in USD, the prompt token
estimate, and the per-token pricing used. An unpriced model
returns priced false and null costs.

Input parameters:

- `max_tokens` (integer)
- `model` (string, required)
- `n_findings` (integer)
- `text_length_chars` (integer, required)

Output parameters:

- `result` (string)

### `repo_scan` (~325 tokens)

Scan a repo with semgrep and osv-scanner, then two-stage triage.

Returns a JSON report: per-finding verdicts with stage and cost,
totals, skipped findings with reasons, the OSV section, and the
estimate versus actual cost. A dry run runs the scanners and
estimates the cost with no GMI calls. Files over max_file_kb are
skipped unless the caller raises the cap. Every triaged finding
is stored in the findings store (per-user
\~/.gmi-security-mcp/findings.db by default) and the report
carries scan_id, with one finding_id per finding. The custom
rules pack runs in addition to the default semgrep config, and
its findings carry source custom-rule. A clean repo_scan does
NOT mean flawless. Writing the report to write_report needs
\--allow-apply on the server command line; without it the scan
still runs but the write is refused.

Input parameters:

- `db_path`
- `dry_run` (boolean)
- `include_tests` (boolean)
- `max_file_kb` (integer)
- `max_files` (integer)
- `max_tokens` (integer)
- `max_total_kb` (integer)
- `repo_path` (string, required)
- `rules_dir`
- `semgrep_config`
- `spend_cap_usd` (number)
- `stage1_model` (string, required)
- `stage2_model` (string, required)
- `threshold` (number)
- `write_report`

Output parameters:

- `result` (string)

### `check_osv_advisory` (~106 tokens)

Check one lockfile against OSV with the local osv-scanner.

Parses the lockfile locally, then runs osv-scanner on it and
returns advisories as facts: id, package, installed version,
fixed version, severity, summary, and link. Packages with only
a version range and no exact version are reported unresolved,
never given a verdict. No GMI call is made.

Input parameters:

- `ecosystem`
- `lockfile_path` (string, required)

Output parameters:

- `result` (string)

### `explain_cve` (~136 tokens)

Explain a CVE, GHSA, or OSV id from its advisory, with citations.

Fetches the advisory from OSV by exact id. When no advisory with
that id exists, returns found false and invents nothing. When a
model is named, GMI writes one plain-language paragraph from the
retrieved advisory only. When no model is named, the explanation
is the advisory summary itself.

Input parameters:

- `advisory_id` (string, required)
- `max_tokens` (integer)
- `package`
- `spend_cap_usd` (number)
- `stage1_model`
- `version`

Output parameters:

- `result` (string)

### `draft_private_disclosure` (~262 tokens)

Draft a private disclosure from a confirmed real finding.

Uses the GitHub Security Lab report template, with the
ssh-mcp-server host-key draft as the worked example of the
format. Refuses when the verdict is not real, or when confidence
is below 0.8 without explicit confirmation. When finding_id is
given, the finding must be in the store with status confirmed,
or triaged with verdict real and confidence at or above 0.8;
otherwise the draft is refused and the result says why.
Returns the draft as Markdown and writes it only when
write_path is given. It is never sent, never opened as a PR,
never forked, never pushed, never emailed. sent is always false.
Writing the draft to write_path needs --allow-apply on the
server command line; without it the call is refused. When
\--require-scope is set, the write target must sit inside a
repo with scope enabled.

Input parameters:

- `confirm_low_confidence` (boolean)
- `db_path`
- `finding` (object, required)
- `finding_id`
- `include_fix` (boolean)
- `maintainer_contact`
- `repo` (string, required)
- `write_path`

Output parameters:

- `result` (string)

### `verify_finding` (~413 tokens)

Verify one finding with a deterministic oracle, PoV-is-truth.

A finding stays a candidate until an oracle reproduces it.
GMI only writes the PoC, when poc is null; the local oracle
decides. code is the audited code and harness description
sent with the finding when a PoC is generated. A generated PoC is returned for review and only runs
when run_poc is true AND confirm_generated_poc is true:
run_poc alone never runs model-generated code on the host
in the same call that generated it. A caller-supplied PoC
runs when run_poc is true, with no extra flag, because the
caller already reviewed it. A false_positive finding is refused
unless regression_check is true, and then the result is
labelled regression, not confirmation. Categories without an
oracle return skipped with "no oracle for this category".
test_command runs a PoC file already in the repo, or the
written PoC when it names {poc}, for example
pytest {poc} -k host_key. The PoC runs on the host by default,
with a warning; pass executor docker for a disposable
container when Docker is available. verify_finding never
applies a fix; a fix_candidate is run through patch
validation and then restored. A fix_candidate needs
\--allow-apply on the server command line; without it the call
is refused.

Input parameters:

- `code`
- `confirm_generated_poc` (boolean)
- `db_path`
- `executor` (string)
- `finding`
- `finding_id`
- `fix_candidate`
- `harness_module`
- `max_tokens` (integer)
- `poc`
- `regression_check` (boolean)
- `repo_path`
- `run_poc` (boolean)
- `spend_cap_usd` (number)
- `stage1_model`
- `test_command`

Output parameters:

- `result` (string)

### `list_findings` (~101 tokens)

List stored finding summaries, newest first.

Filters: status, check, severity, repo_path. limit defaults
to 20 and is capped at 100. cursor pages through results.
Summaries only: no code in list output, only in get_finding.

Input parameters:

- `check`
- `cursor`
- `db_path`
- `limit` (integer)
- `repo_path`
- `severity`
- `status`

Output parameters:

- `result` (string)

### `get_finding` (~54 tokens)

Get one stored finding in full: code, evidence, verdict
history, pipeline events, verification results, business
impact, and matching triage memories.

Input parameters:

- `db_path`
- `finding_id` (string, required)

Output parameters:

- `result` (string)

### `update_finding` (~141 tokens)

Update a stored finding. reason is required.

business_impact changes business impact only, never technical
severity, verification, review gates, or patch permissions.
status moves one step at a time and is refused when it skips a
state, for example new to confirmed without a reproduced
verification. Suppressing a critical/high finding with business
impact Urgent/High is refused unless force is true with a
reason, and is then recorded with that reason and actor.

Input parameters:

- `business_impact`
- `db_path`
- `finding_id` (string, required)
- `force` (boolean)
- `reason`
- `status`

Output parameters:

- `result` (string)

### `mark_fp` (~104 tokens)

Mark a stored finding false_positive. reason is required.

Creates a triage memory with the given scope (global, package,
or target, default target). The memory is a hint only: it never
auto-rejects a future finding, and the agent must still triage
it. Memories are created only by this human call.

Input parameters:

- `db_path`
- `finding_id` (string, required)
- `reason` (string, required)
- `scope` (string)

Output parameters:

- `result` (string)

### `mark_confirmed` (~72 tokens)

Mark a stored finding confirmed. reason is required.

Only when a verification result with status reproduced exists
for the finding. Otherwise the call is refused, and an LLM
verdict alone cannot set confirmation.

Input parameters:

- `db_path`
- `finding_id` (string, required)
- `reason` (string, required)

Output parameters:

- `result` (string)

### `list_rules` (~93 tokens)

List the custom semgrep rules pack. No GMI call, no spend.

Returns each rule with id, name, category, severity,
description, and whether it is enabled by default. category
filters to one of the 7 known checks. The pack ships in
src/gmi_security_mcp/rules/; set GMI_SECURITY_MCP_RULES_DIR when
it is elsewhere.

Input parameters:

- `category`

Output parameters:

- `result` (string)

### `scope_enable` (~83 tokens)

Enable scope for one repo from a scope file.

A scope file alone never activates checks; only this call
does. Returns the in-scope and out-of-scope lists and a
warning that scope is a destination policy, not authorisation
to test, and not an OS sandbox.

Input parameters:

- `repo_path` (string, required)
- `scope_file` (string, required)

Output parameters:

- `result` (string)

### `scope_disable` (~52 tokens)

Disable scope for one repo.

Returns disabled with a warning that tools will now refuse
if --require-scope is set, because there is no scope policy
for the repo.

Input parameters:

- `repo_path` (string, required)

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/jayanng-gmi-security-mcp/gmi-security-mcp#diagnostics

## Score history

- 2026-11-21: 65
- 2026-11-20: 79
- 2026-11-19: 64
- 2026-11-18: 63
- 2026-11-17: 63
- 2026-11-16: 62
- 2026-11-15: 62
- 2026-11-14: 76
- 2026-11-13: 61
- 2026-11-12: 75
- 2026-11-11: 60

## Common questions

### What is the gmi-security-mcp server?

gmi-security-mcp is listed in the public MCP registry as io.github.Jayanng/gmi-security-mcp. Triage semgrep findings with GMI Inference, with cost shown before every run. This page covers its PyPI package (gmi-security-mcp).

### Is the gmi-security-mcp server safe to use?

gmi-security-mcp scores 65 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the gmi-security-mcp server expose?

gmi-security-mcp exposes 15 tools: triage_semgrep_finding, estimate_cost, repo_scan, check_osv_advisory, explain_cve, and 10 more. Their descriptions and schemas cost roughly 2,249 tokens of context every time the server is loaded.

### Is the gmi-security-mcp server still maintained?

gmi-security-mcp is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the gmi-security-mcp server under?

gmi-security-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the gmi-security-mcp server?

VerifyMCP ran 15 checks on gmi-security-mcp, covering Known CVEs, Install scripts, Dependency health, Source repository and 11 more. One item could not be completed, a gap on our side rather than a finding about gmi-security-mcp: Malware scan. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/gmi-security-mcp/
- Socket report: https://socket.dev/pypi/package/gmi-security-mcp
- Repository: https://github.com/Jayanng/gmi-security-mcp
- Changelog RSS feed: https://verifymcp.io/servers/jayanng-gmi-security-mcp/gmi-security-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/jayanng-gmi-security-mcp/gmi-security-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/jayanng-gmi-security-mcp/gmi-security-mcp.json
- HTML version of this page: https://verifymcp.io/servers/jayanng-gmi-security-mcp/gmi-security-mcp
