MCP.Market

Groundwork MCP server

by nickjlamb·io.github.nickjlamb/groundwork·v0.4.1·1 stars
No reviews yet

Deployment-readiness checks for document-QA and extraction AI: grounding, extraction, CI gate.

A85/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A85/100

full report

Adoption
Growing

1 stars14 downloads/wk

Reviews

Write one

Nobody has reviewed Groundwork yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Groundwork tools (5, 3 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • check_answer_grounding

    Deterministically check a single answer against the context it should be grounded in: required facts (anchors) present, every number traceable to the context, abstention when the question is unanswerable. Same logic as the CI gate — no model, no network. Returns pass/fail with named issues.

  • check_extraction

    Deterministically check a structured extraction against its hand-labelled gold record: schema validity (nullable fields are the abstention contract), field accuracy with per-field normalisers (dates → ISO, money → minor units) and aliases, and fabrication — a non-null value in a field whose gold is null (a guessed date of birth the document never stated). Same logic as the CI gate — no model, no n

  • check_readinesswrite action

    Run `groundwork check` in a repo that has a scaffolded harness: redaction self-test, then the archetype's eval (grounding for document-qa, extraction for extraction) against the repo's own gold set. Returns the exit code, the main scorer's metrics, and any named failures — exactly what CI would report.

  • cost_summarywrite action

    Run `groundwork cost` in a repo: measured token usage from eval runs, with savings recommendations in leverage order (prompt caching, batching, context trimming, model routing last).

  • scaffold_harnesswrite action

    Run `groundwork init [archetype]` in a repo: writes the adapter boundary, redaction config, gold-set templates, GitHub Action, and playbook for a deployment pattern — document-qa (documents → grounded answers) or extraction (documents → structured fields). Never overwrites existing files. After scaffolding, the human wires groundwork/adapter.mjs and replaces the example gold cases with real ones.

Public scan report

scanner v0.1.10 · 2026-09-28 · same rubric, same numbers if you re-run it

1 medium
  • Code scan32 source files scanned20/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (1)

  • mediumeval / new Function usedexec.eval
    dist/commands/check.js: …ut, no residue; // 2. the archetype's eval (OpenGATE) through the repo's adapter and…
Overall 85/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Groundwork compares

Against every graded Developer tools MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
85/100
higher than 70% of 1,119 Developer tools servers
Tools
5
the typical Developer tools server has 7
Tools that change things
60%
typical: 5%. Fewer write tools means less an agent can break
GitHub stars
1
more than 50% of 855 Developer tools servers
Downloads a week
14
more than 3% of 436 Developer tools servers with a package

What its tools let an agent do: 2 read · 3 change

Install Groundwork in Claude Code, Cursor or VS Code

Runs npx -y @pharmatools/groundwork on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add groundwork -- npx -y @pharmatools/groundwork
Add to Cursor

What the publisher says

From the Groundwork repository's README, as published. We do not edit it. Read it on GitHub

Groundwork

Deployment-readiness harnesses for AI deployment patterns.

Redaction · evals from your real failures · a CI gate that fails fabrication

Website · Getting started · Examples · Roadmap · Contributing · Changelog

You have a prototype: your documents, a model, useful output. What you don't have is the apparatus that makes it responsible to ship — a privacy pre-step, an evaluation built from your own failures, and a gate that stops a quiet prompt tweak from deploying a system that fabricates. That apparatus usually requires an ML engineer. Groundwork scaffolds it instead.

Groundwork's units are deployment patterns, not products — think Terraform modules for trustworthy AI deployments. groundwork init scaffolds the whole harness for a pattern:

Every check is deterministic: same inputs, same result, every time — no LLM judge, and no API key for the checks themselves.

Quick start — 60 seconds, no API key

git clone https://github.com/nickjlamb/groundwork.git && cd groundwork
npm install && npm run build
npm run demo          # document QA: the whole loop passes, fully offline
npm run demo:break    # the system starts fabricating — watch the gate go red
✗ GROUNDING demo-savings: ungrounded number "14" — not in the provided context
✗ GROUNDING demo-unanswerable-appeals: unanswerable question — the answer did not abstain

The same loop for structured extraction:

npm run demo:extraction         # documents → fields, every check green
npm run demo:extraction:break   # a guessed date of birth, a dropped field — red, by name
✗ EXTRACTION demo-referral: SCHEMA: /referral_date must be string
✗ EXTRACTION demo-referral: FABRICATED field "date_of_birth": document does not state it (got "12 April 1988")

That red build is the product: a fabricated figure, a guessed field, or a failed abstention becomes a CI failure, not a user complaint.

Ready for your own system?

npm install -D @pharmatools/groundwork
npx groundwork init                # document QA
npx groundwork init extraction     # structured extraction

How it works

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Groundwork: common questions

Is Groundwork MCP server safe?
Yes, by our scan: it is graded A (85/100). Read the Groundwork safety report
How do I install Groundwork?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Groundwork need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Groundwork maintained?
The last commit was 37 days ago (2026-09-28). The latest release is v0.4.1.
What can I use instead of Groundwork?
Servers from other publishers that do the same job: Dot AI MCP server, Komodo MCP Server and argot MCP server.
How does Groundwork compare with other Developer tools MCP servers?
safety score 85/100 (higher than 70% of 1,119 Developer tools servers); tools 5 (the typical Developer tools server has 7); tools that change things 60% (typical: 5%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Groundwork

Same job from other publishers: the closest match first, then the best rated.

  • Dot AI
    AI-powered development platform for Kubernetes deployments and intelligent automation
    A
  • Komodo MCP Server
    MCP server for Komodo - manage Docker containers, servers, stacks, and deployments via AI
    B
  • argot
    Read-only context and complete checks against patterns learned from git history. Local; no LLM.
    B
  • Vercel
    MCP server for Vercel — manage deployments and view build and runtime application logs.
    A
  • RepoPilot
    Local, deterministic review of Git changes: weakened tests and CI gates, risky flows, blast radius.
    A

More from nickjlamb →