Groundwork
Deployment-readiness checks for document-QA and extraction AI: grounding, extraction, CI gate.
Connector by nickjlamb · GitHub account verified by the MCP Registry
Install
Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.
npx agentmarket install connector/nickjlamb-groundwork
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 26, 2026.
- Tools
- 2 read · 2 write · 0 delete · 1 not yet classified
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Node.js package
Tools by what they do 5
Read from the source code; the running server may list different tools.
Read 2 · Look things up without changing anything.
check_answer_groundingcheck_extraction
Write 2 · Create, change, send or run things.
cost_summaryscaffold_harness
Not yet classified 1 · We could not tell from the name and description.
check_readiness
Network hosts it talks to 2
github.com· found in codeglama.ai· found in code
Files it touches
- Any path the agent passes to its tools
Tools (5)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
check_answer_groundingCheck one answer's groundingDeterministically 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_extractionCheck one extracted recordDeterministically 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 network. Returns pass/fail with named issues and a per-field verdict.
check_readinessRun the readiness gate on a repoRun `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_summarySummarise measured token costsRun `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_harnessScaffold the readiness harness into a repoRun `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.
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit
- Sep 29, 2026 (29 days ago)
- Last release
- Sep 28, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- Registry name
io.github.nickjlamb/groundwork- Version
- 0.4.1
- Auth
- No auth
- Packages
- npm @pharmatools/groundwork
- License
- License unknown
- Repository
- github.com/nickjlamb/groundwork
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
More from nickjlamb
- 0.648score
Pubcrawl
nickjlamb
PubMed & Europe PMC literature search, US/UK drug labelling, and clinical trials for AI assistants.
ConnectorAFreshness: ALocalRead-only★ 15Claude Code +5 - 0.638score
Redacta MCP
nickjlamb
Keep patient identifiers out of AI agent context — a local privacy boundary for healthcare agents.
ConnectorAFreshness: ALocal★ 8Claude Code +5 - 0.605score
AI Footprint
nickjlamb
Water and energy footprint of AI use: chat prompts, agent sessions, methodology and sources.
ConnectorAFreshness: ARemoteRead-only★ 1Claude Code +3 - 0.602score
Opengate MCP
nickjlamb
Check whether an AI answer is grounded in its context — deterministic, no LLM judge.
ConnectorAFreshness: ALocalRead-only★ 1Claude Code +5 - 0.602score
Studydiff
nickjlamb
Explain why two scientific papers disagree, every claim grounded in a verbatim source quote.
ConnectorAFreshness: ALocal★ 1Claude Code +5
Cite this page
Groundwork MCP server. Agent Mart. https://agentmart.dev/connectors/nickjlamb-groundwork (last updated 2026-10-24)