harness-fleet (NatesVibeCode/harness-fleet) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 17 tools. No publisher has claimed this listing.

C
Emerging
74/100

harness-fleet

Typed bulk evidence processing with SQLite checkpoints, exact source offsets, CLI, MCP, and Agent Skills.

Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. 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

NatesVibeCode

Source: github_repo_search

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 →

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.

// key findings
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 1 credential: OPENROUTER_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes17 tools

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.

harness_fleet_routes

List admitted routes; optionally append fresh provider price observations.

harness_fleet_cooldowns

Inspect active rate-limit route cooldowns or clear them.

harness_fleet_init

Initialize and register a typed task from a built-in preset (score, filter, triage, classify, extract, summarize).

harness_fleet_register_task

Validate and register one immutable, declarative task revision.

harness_fleet_tasks

List the current registered task names and their exact revision IDs.

harness_fleet_save_profile

Persist and activate one immutable Ideal Company Profile revision.

harness_fleet_get_profile

Return the active Ideal Company Profile stored in SQLite.

harness_fleet_test

Run one real inference batch and return only typed, source-grounded results.

harness_fleet_validate

Validate a task and all input records offline without invoking a model.

harness_fleet_run

Create and execute a bounded, resumable SQLite-backed bulk campaign.

harness_fleet_resume

Resume pending batches from an existing run without rereading source files. Paid routes must be explicitly approved again in each new session; free routes remain the default.

harness_fleet_status

Show real-time progress, batch status counts, and per-route reliability metrics for a run.

harness_fleet_history

Show an entity's score trajectory across rescore rounds, oldest first.

harness_fleet_eval

Benchmark candidate routes against test samples and update intelligent ranking priors.

harness_fleet_export

Export verified records as a self-validating typed packet (JSON) or flat CSV. For comparable ranking, pin Phase-B to one judge route; use adjust_scores only when mixed raters are unavoidable.

harness_fleet_schema

Return an admitted JSON Schema or the authoritative SQLite schema.

harness_fleet_doctor

Check workspace SQLite state, provider availability, and usable routes.

// 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.
configHARNESS_FLEET_DB
🔐 secretOPENROUTER_API_KEYIf is set in your shell, passes it into that client config too (values are never printed), so OpenRouter routes work from the desktop app.
configXDG_CONFIG_HOME
configPYTEST_CURRENT_TEST
// 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

17/17 tools missing one or more hints — harness_fleet_routes (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); harness_fleet_cooldowns (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); harness_fleet_init (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +14 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.

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 2 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/natesvibecode/harness-fleet)](https://m8ven.ai/mcp/natesvibecode/harness-fleet)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: cd8d9dce8842bc4715042e6f77af2b78a33458c5
code hash: 13f8236c75b88e5a13d9b1973dae44ccd2c0caf15d871714ca7aba048f9931eb
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