Acture MCP
Turns raw engineering signals into narrative reports by exposing GitHub data via MCP, enabling AI agents to generate structured, shareable engineering summaries.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
vkhafizov
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
analyze_code_changesAnalyze git diff, blame, and commit history for the local repository
commit_diffGet the diff (changes) for a specific commit using GitHub API. Shows file statistics and optionally the full patch.
linked_prsFind pull requests linked to an issue via mention in PR body/title (e.g., "Fixes #123", "Closes #123"). Uses GitHub search API.
list_issuesList GitHub issues for a specific period using gh CLI. Returns issues created or updated within the specified date range.
pr_commitsGet all commits from a pull request with essential metadata (sha, message, author, date). Uses GitHub CLI.
read_docRead full content of a documentation file. Use after search_docs to get complete file content.
read_issueRead a specific GitHub issue by number using gh CLI. Returns full issue details including body and comments.
repo_metricsCollect engineering metrics and DORA approximations for stakeholder reports. Tracks velocity, quality, and delivery performance over a configurable time period.
search_codebaseSearch across GitHub entities. For code search: uses local repository (fast, no limits). For other types: uses GitHub API.
search_docSearch documentation using MiniSearch. Indexes all documentation files and provides fast, relevance-ranked search with fuzzy matching.
publish_notion_reportPublishes structured report to Notion. Supports: weekly_engineering, milestone_review, daily_standup. Provide whatever data you have; the tool will format it appropriately.
read_notion_reportsList saved Notion reports or fetch report content. No arguments = list all reports. Provide report_id to fetch specific report content.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
axios Vulnerable to Full Man-in-the-Middle via Prototype Pollution Gadget in `config.proxy`
axios Vulnerable to Credential Theft and Response Hijacking via Prototype Pollution Gadget in Config Merge
Axios is Vulnerable to Denial of Service via __proto__ Key in mergeConfig
Axios: Header Injection via Prototype Pollution
XDG_CONFIG_HOMETool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
12/12 tools missing one or more hints — analyze_code_changes (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); commit_diff (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); linked_prs (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +9 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tests exist
No test files found
Add tests that exercise each declared tool.
Shell command execution
7 calls in production code run through a shell (src/cli/utils/gh-manager.js:49, src/cli/utils/gh-manager.js:70, src/cli/utils/gh-manager.js:81)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
No arbitrary install scripts
Has postinstall/preinstall script — runs arbitrary code on npm install
Remove postinstall/preinstall hooks unless they’re essential.
Production dependencies are patched
0 critical, 12 high severity in production deps — @modelcontextprotocol/sdk@0.5.0 (high), axios@1.13.3 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/vkhafizov/acture-mcp)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check