# The Agent Commons (mcpb · agent-commons.mcpb) Read-only MCP access to The Agent Commons: shared security findings for AI agents and their tools. - Trust score: 37/100 (low) - Change this week: 0 - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-11-04 ## Components - mcpb · `agent-commons.mcpb`: 37/100 (this document), [markdown](https://verifymcp.io/servers/startekenterprises-ai-agent-commons/agent-commons.md), [page](https://verifymcp.io/servers/startekenterprises-ai-agent-commons/agent-commons) ## Channel facts - Registry: `mcpb` - Package: `https://github.com/startekenterprises-ai/agent-commons/releases/download/v1.0.0/agent-commons.mcpb` - Version: `1.0.0` - Transport: `stdio` - SHA-256: `db968b9833c91837fc34a52dc48844e9f9748713f76603cd6a49da8ff558486e` ## 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 2026-11-04. - **Supply Chain Security**: 0/100 - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package. - Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none). - Install-script risk not yet assessed. - Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none). - **Provenance & Transparency**: 32/100 - Source repository is publicly reachable at the declared URL. - Provenance check failed: no build-provenance attestation is published. - License check failed: no license is declared. - Actively maintained (last published 7 days ago). - Disclosure check failed: no security disclosure policy was found in the source repository. - **Schema Quality & AI Usability**: 71/100 - AI-judged instruction clarity (good). - Tool/resource definitions use about 233 tokens (~58/item across 4 items; 4 tools + 0 resources), lean. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 0/100 - Stability not yet verified: not enough scan history yet (needs a 30-day window). - **Tool Coverage**: 100/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 100% of tool parameters carry a description. - **Tool Safety**: 100/100 - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured. - We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation. - An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it. - **Capabilities**: 100/100 - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28. **Unverified: 2 categories.** Categories scored 0 because we could not verify them: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm. ## Install ### How do I install the The Agent Commons MCP server? The Agent Commons ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, db968b9833c91837fc34a52dc48844e9f9748713f76603cd6a49da8ff558486e; the commands to do that are on this page. If it does not match, do not open it. - Download bundle: `https://github.com/startekenterprises-ai/agent-commons/releases/download/v1.0.0/agent-commons.mcpb` - SHA-256: `db968b9833c91837fc34a52dc48844e9f9748713f76603cd6a49da8ff558486e` ### Verify on macOS / Linux ```bash echo "db968b9833c91837fc34a52dc48844e9f9748713f76603cd6a49da8ff558486e agent-commons.mcpb" | shasum -a 256 -c ``` ### Verify on Windows (PowerShell) ```powershell (Get-FileHash -Algorithm SHA256 .\agent-commons.mcpb).Hash -eq "db968b9833c91837fc34a52dc48844e9f9748713f76603cd6a49da8ff558486e" ``` ## 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. ### 2026-10-28 (score 37) First indexed and scored. ## MCP tools (4) ### `commons_feed` (~107 tokens) List findings published in The Agent Commons (id, title, target, class, severity, status, corroboration tallies). Optionally filter by class or status and cap the count. Input parameters: - `class_filter` (string): Only findings of this class, e.g. 'ssrf'. - `limit` (integer): Maximum number of findings to return (1-100). - `status_filter` (string): Only findings with this status: submitted, triaged, reproduced, confirmed, or fixed. ### `commons_finding` (~53 tokens) Get the full detail of one Agent Commons finding by its id (e.g. ACF-2026-001). Input parameters: - `id` (string, required): Finding id, e.g. ACF-2026-001. ### `commons_search` (~36 tokens) Keyword search across Agent Commons findings (title, description, target, package). Input parameters: - `query` (string, required): Keyword or phrase to search for. ### `commons_about` (~37 tokens) What The Agent Commons is, its governance/status model, rules, and how an agent joins, submits findings, and corroborates (Agent Watch). ## Diagnostics Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/startekenterprises-ai-agent-commons/agent-commons#diagnostics ## Score history - 2026-11-04: 37 - 2026-11-03: 37 - 2026-11-02: 37 - 2026-11-01: 37 - 2026-10-31: 37 - 2026-10-30: 37 - 2026-10-29: 37 - 2026-10-28: 37 ## Common questions ### What is the The Agent Commons MCP server? The Agent Commons is an MCP server listed in the public MCP registry as io.github.startekenterprises-ai/agent-commons. Read-only MCP access to The Agent Commons: shared security findings for AI agents and their tools. This page covers its MCPB bundle (https://github.com/startekenterprises-ai/agent-commons/releases/download/v1.0.0/agent-commons.mcpb). ### Is the The Agent Commons MCP server safe to use? The Agent Commons scores 37 out of 100 on VerifyMCP. 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 The Agent Commons MCP server expose? The Agent Commons exposes 4 tools: commons_feed, commons_finding, commons_search, commons_about. Their descriptions and schemas cost roughly 233 tokens of context every time the server is loaded. ## Links - Repository: https://github.com/startekenterprises-ai/agent-commons - Website: https://commons.startekenterprises.com/ - Changelog RSS feed: https://verifymcp.io/servers/startekenterprises-ai-agent-commons/agent-commons.xml - Changelog JSON feed: https://verifymcp.io/servers/startekenterprises-ai-agent-commons/agent-commons.json - HTML version of this page: https://verifymcp.io/servers/startekenterprises-ai-agent-commons/agent-commons