mcp-agent (lastmile-ai/mcp-agent) is an MCP server listed on the M8ven Trust Index. It scores 98 out of 100, grade A. It declares 11 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
A
Trusted
98/100
8 days ago

mcp-agent

Build effective agents using Model Context Protocol and simple workflow patterns

→ lastmile-ai/mcp-agent· listed on mcp_so

Trusted. Deep verification, no outstanding findings, and an established reputation. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

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

lastmile-ai

Source: mcp.so · also listed on github_topic, github_code

Maintenance & responsiveness
as of 2026-08-19
Issues closed (90d): 16 · 146 open
Releases (90d): none — last 2025-05-09
Contributor retention: 0/12 stayed · 0 active
Is this your MCP?

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 →

⚡ Connect GitHub for Live Monitored

Install from

mcp.soGitHubGitHub

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
🚨
Secret credentials may flow to a network call
5 flows detected: MCP_GATEWAY_TOKEN. We can’t prove the destination matches the brand the credential belongs to.
🔐
You'll be asked for 6 credentials: MCP_GATEWAY_TOKEN, OPENAI_API_KEY, ANTHROPIC_API_KEY, GOOGLE_API_KEY, AZURE_API_KEY, AWS_SECRET_ACCESS_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
🔐 secretMCP_GATEWAY_TOKEN
configMCP_GATEWAY_URL
configLOG_SECRETS
configMCP_GATEWAY_TIMEOUT
configMCP_GATEWAY_REQUEST_TIMEOUT
configXDG_CONFIG_HOME
🔐 secretOPENAI_API_KEYAdd openai API key to mcp_agent.secrets.yaml or set
🔐 secretANTHROPIC_API_KEY
🔐 secretGOOGLE_API_KEY
🔐 secretAZURE_API_KEY
configAWS_ACCESS_KEY_ID
🔐 secretAWS_SECRET_ACCESS_KEY
configEDITOR
configVISUAL
configMCP_VERBOSE
// quality suggestions

Tool 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

13/13 tools missing one or more hints — workflows-list (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); workflows-runs-list (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); workflows-run (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +10 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.

Tool test coverage

Only 1/13 tools referenced in tests (8%)

Write tests that reference each tool by name so every tool has at least one test.

Secrets stay with their owner

5 secrets sent to a request target we could not resolve (MCP_GATEWAY_TOKEN → dynamic, MCP_GATEWAY_TOKEN → dynamic) — often a configured endpoint, not necessarily third-party

Audit where credentials are sent. A NOTION_TOKEN should only reach api.notion.com — never a third-party host.

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.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/lastmile-ai/mcp-agent)](https://m8ven.ai/mcp/lastmile-ai/mcp-agent)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: f62d849350816588b1c6294e7914bbe4d8b84072
code hash: 9756ccff0643b31f7131e8a44a37d5cdfa31c0d563ef0bf94c1f5be41d624afa
verified: 9/3/2026, 11:01:42 AM
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

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
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client