dod-mcp
Lets DoD evidence criteria use values collected from GitHub, such as commit-linked checks, and validates the evidence's form, age, commit, and value.
Lets customer-request DoD criteria use helpdesk evidence, such as first-response timestamps fetched via a helpdesk tool, and checks them against the agreed deadline.
Lets DoD evidence criteria use Jira-sourced ticket evidence and checks it against the team's Definition of Done criteria.
Lets DoD evidence criteria use SonarQube quality-gate evidence for the relevant commit and validates its form, age, commit, and value.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@dod-mcp get the DoD for a software development ticket labeled backend"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
dod-mcp
An MCP server that serves a team's Definition of Done from versioned YAML files, one file per task type, and checks the evidence an agent collected against it, criterion by criterion. It never declares an item done.
Prototype, November 2026, built with Claude Code as co-developer. All data in this repository is fictional.
Problem
The Definition of Done usually lives on a wiki page or in a pull request template. The pipeline checks part of it (build, tests, quality gate); people check the rest from memory in the review. Coding agents make this worse: they deliver more changes in less time, they report "done" when the tests are green, and they cannot see criteria that are written down nowhere they look (documentation, sign-offs, operations).
This server keeps the DoD in the team repository, as a shared base plus one file per task type (software development, documents, customer requests …). Agent and people read the same files. The server checks an item against them and reports, per criterion, a status and the evidence or what is missing. Whether the item is done stays the team's decision.
Related MCP server: Spec Kit Acceptance Gate MCP
What it does
Tool | What it does |
| The DoD for a ticket: pass its ticket type and labels. Every criterion of base and type with its origin and check kind, and for evidence criteria which tool delivers the value and what it must show. Without arguments: the list of task types. |
| The evidence the agent collected (source, tool, arguments, time, raw value, commit) against the DoD: |
| Acceptance criteria against the rules of their type: Given/When/Then complete and in order, observable Then steps, vague words, numbers without units, required fields and formats. Every finding with line and column. |
| What changed between two versions of a type (each with its base) or of the base, every entry with its origin. For DoD reviews and retrospectives. |
Resource | Content |
| base, mapping and every task type with version label, validity, errors and recorded versions |
| one resource per type file: base and type merged, every criterion with origin, file and line |
| an earlier version, with the base it was first served with |
| the template for acceptance criteria and the rules the lint applies |
| the judgment criteria with question and standards for plausible and doubtful |
Prompt | Does |
| determines the type, collects evidence with your other servers, runs |
All tools are read-only. The server calls no model and holds no credentials for other systems.
Who decides what
Who | Words | For what |
Server |
| each criterion, from evidence and rules, reproducible |
Model in the client | plausible / doubtful | each judgment criterion, with a quote, by the rubric |
Team or a named role | "done" | the item; a role confirms attestation criteria |
Each criterion says how it is checked: evidence (a value a tool can fetch, such as the quality gate of this commit), judgment (a question, such as "which acceptance criterion has no test?") or attestation (a role confirms, such as operations for the runbook). The agent fetches evidence through the official servers (SonarQube, Azure DevOps, GitHub, Jira …) and passes it on unchanged; the server checks its form, age, commit and value. The reasoning is in docs/design.md.
Quick start
Requires Node.js 26; Docker for the container.
npm install
npm run build
npm testLocal, over stdio
claude mcp add --transport stdio --scope local dod --env DOD_DIR=/absolute/path/to/your/dod -- node /absolute/path/to/dod-mcp/dist/main.jsThen ask Claude Code "Check DEMO-42 against our Definition of Done", or run the prompt as /mcp__dod__done_check DEMO-42 (Claude Code names MCP prompts /mcp__<server>__<prompt>). Without DOD_DIR the server serves the fictional example in dod/.
In a container, over HTTPS
scripts/dev-cert.sh # self-signed certificate and a token in local/secrets/ (git-ignored)
docker compose up -d --build # https://localhost:8443/mcp, the example DoD mounted read-only
claude mcp add --transport http dod https://localhost:8443/mcp --header "Authorization: Bearer $(cat local/secrets/tokens)"Start Claude Code with NODE_EXTRA_CA_CERTS pointing to local/secrets/cert.pem, so it trusts the certificate. One container serves one team: one DoD folder, one database, one set of tokens.
Your team's DoD
dod/
base.yaml # applies to every type
types.yaml # ticket type / label → task type
software-dev.yaml # one file per task type; the file name is the type# FICTIONAL EXAMPLE: dod/kundenanfrage.yaml
type: kundenanfrage
version: 3
title: Kundenanfrage
extends: base
criteria:
- id: FRIST
text: Die erste Antwort ging innerhalb der vereinbarten Frist raus.
check: evidence
source: helpdesk.first_response
expect: { field: first_response_at, not_after: due_at }
fetch_with: [helpdesk:get_ticket]
- id: VOLLSTAENDIG
text: Die Antwort geht auf jede Frage der Anfrage ein.
check: judgment
question: Welche Frage der Anfrage bleibt in der Antwort offen?
- id: ZUSAGE
text: Zusagen zu Preis oder Termin sind freigegeben.
check: attestation
role: VertriebA type may only add to the base. A type file that reuses a base id, uses a key such as
removeoroverride, or lacksextends: baseis invalid, with file, line and column. Other types keep working.A new type is a new file. It appears as resources without a restart and without code changes.
Every change of content raises
version. The server records every version it sees in its database; a changed file with an old version number is invalid (version_not_bumped). The YAML files stay the source of truth and change by pull request.expecthas six operators:equals,one_of,min,max,present,not_after;fieldreads nested values with a dotted path.Acceptance rules come in five kinds:
gherkin,observable_then,vague_words,numbers_need_units,fields(linesName:or headings## Name).
Check the folder in CI with the same loader:
node dist/cli/validate.js dod # prints file:line:column code: message; exit 0, 1 or 2Example (fictional)
check_dod on examples/evidence/software-dev-gaps.json, a story whose quality gate was fetched for another commit, whose test results are 30 hours old, and that no second person has looked at:
Criterion | Origin | Check | Status | Finding | Hint or question |
ERGEBNIS-VERLINKT | base | evidence | met | – | |
FOLGEARBEIT | base | judgment | needs judgment | – | Welche offene Folgearbeit aus dem Ergebnis ist noch nicht als eigenes Item erfasst? |
ZWEITE-PERSON | base | attestation | not met | attestation_missing | Ask the role Teammitglied to confirm; the agent does not confirm on its own. |
QUALITY-GATE | software-dev | evidence | not met | evidence_other_ref | Fetch with get_project_quality_gate_status for commit 9f2c1ab. |
BUILD | software-dev | evidence | met | – | |
TESTS | software-dev | evidence | not met | evidence_stale | Fetch with get_test_results for commit 9f2c1ab. |
TESTAENDERUNG-AUSGEWIESEN | software-dev | evidence | met | – | |
KRITERIEN-GETESTET | software-dev | judgment | needs judgment | – | Zu welchem Akzeptanzkriterium fehlt ein Test, der genau dieses Verhalten prüft? |
RUNBOOK | software-dev | attestation | met | – |
4 met, 3 not met, 2 need judgment, about 1,000 tokens of output. lint_acceptance_criteria on examples/acceptance/software-dev.md finds two incomplete scenarios, an unobservable Then ("ist zufrieden"), a number without unit ("in unter 2") and two vague words; the fixed version is clean. The run is in docs/verification.md.
Configuration
Environment variables only.
Variable | Default (stdio / container) | Purpose |
|
| transport |
|
| DoD folder |
|
| version history; |
| – / | HTTPS port |
| – / | certificate and key (PEM) |
| – / | bearer tokens, one per line, at least 32 characters |
| – / | accepted |
| – / empty | accepted |
Security
HTTPS only; no plain-HTTP mode. Host and Origin are checked before the token, the token before anything else. Tokens come from a mounted file, never from an environment variable, and are never logged.
The container runs as a non-root user on a read-only file system; only
/datais writable. The DoD folder is mounted read-only.No regular expressions from YAML, an alias limit for YAML, size limits for files, evidence and request bodies.
The database holds DoD file versions only: no evidence, no acceptance texts, no request data.
Evidence comes from the agent. The server checks form, age, commit and value, not authenticity; for criteria where a forged value would be expensive, run the same check in CI (an open point).
Limits
The server cannot tell whether evidence is genuine or who gave a confirmation; word lists miss paraphrases; the number rule relies on German nouns being capitalised; the version history starts with the first sync. expect cannot yet compare two fields with each other or compute deadlines relative to another time. Details: docs/design.md, sections 12 and 16.
How this was built
The starting point was a concept sketch for a team MCP server "Definition of Done" (14 November 2026). I defined the problem and the design rules from my two earlier MCP servers (deterministic findings with a location, judgment in the client model, nothing set to done automatically), approved the design (docs/design.md) and reviewed each of the five phases before the next one started. Claude Code drafted the code, the tests and the documentation.
To test the format against reality, a draft DoD was extracted read-only from one real repository. That draft stays outside this repository; it led to two format changes (nested fields in expect, headings as fields) and to the open points on field comparison and deadlines.
Licence
MIT, see LICENSE.
Available Tools
4 toolscheck_dodCheck an item against its Definition of DoneARead-onlyIdempotent
Check the evidence you collected for an item against its DoD. For every evidence criterion, fetch the value with the tool named in get_dod and pass it unchanged: criterion, source, tool, arguments, retrieved_at (ISO 8601 with time zone), raw and, for commits, ref. Never invent or retype values; leave out what you could not fetch. Returns met / not_met / needs_judgment per criterion with findings (evidence_missing, evidence_stale, evidence_other_ref …) and a hint on how to get missing evidence. There is no overall status: the team decides whether the item is done. Read-only; writes nothing to the ticket.
Inputs: item (required), as_of, evidence. Returns: item, type, as_of, limits, +6 more
diff_dodCompare two versions of a DoDARead-onlyIdempotent
What changed in the Definition of Done of a task type between two versions of its file, each merged with its base, or between two versions of the base (type: "base"). Every added, removed or changed criterion and rule names its origin. Defaults: from the previous recorded version to the DoD in force now. For DoD reviews and retrospectives. Read-only.
Inputs: type (required), to, from. Returns: to, from, type, rules, +4 more
get_dodGet the Definition of DoneARead-onlyIdempotent
The Definition of Done for a ticket: pass ticket_type and labels as they are in the ticket (or type explicitly). Returns every criterion of base and type with its origin and check kind: evidence (which source and tool deliver it, what value is expected, how old it may be), judgment (a question you answer with rubric://dod/{type}) or attestation (a role confirms). Without arguments: the list of task types. An ambiguous or unknown type is an error with a hint, never a default. Read-only.
Inputs: type, labels, ticket_type. Returns: dod, overview, resolution
lint_acceptance_criteriaLint acceptance criteriaARead-onlyIdempotent
Check acceptance criteria against the rules of their task type: Given/When/Then complete and in order, observable Then steps, vague words, numbers without units, required fields and formats. Pass the text as it is in the ticket plus ticket_type and labels (or type). Every finding has line, column, rule and a hint; template://{type} shows the expected form. Deterministic and read-only; it does not rewrite the text.
Inputs: text (required), type, labels, ticket_type. Returns: type, limits, summary, findings, +4 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a distinct verb-purpose: get_dod retrieves criteria, check_dod validates collected evidence, lint_acceptance_criteria validates AC text, diff_dod compares versions. The only mild overlap is get_dod's no-argument mode (listing task types) and its role as the prerequisite for check_dod, but descriptions make the pipeline order explicit.
All four names follow a clean verb_noun snake_case pattern (get_, check_, lint_, diff_), with the DoD-related tools sharing a consistent _dod suffix. No mixed conventions or casing.
Four tools is small but each covers a genuinely different operation in a narrow read-only domain, so nothing feels padded. It is on the thin side — no write/attestation tools exist — but that appears intentional for a read-only DoD reference service.
The read-only lifecycle (fetch criteria, check evidence, lint AC, diff versions) is covered, but check_dod returns needs_judgment pointing at rubric://dod/{type} and lint points at template://{type} with no tool to retrieve either, creating dead ends unless resources fill the gap. There is also no way to record judgment outcomes or attestations.
Maintenance
Related MCP Connectors
Read-only release evidence for coding agents: findings, deliveries, source and runtime data.
Task contract, evidence check and done gate for AI coding agents. Read-only, no sign-in.
Read-only, deterministic AI triage and readiness tools implementing Sophon's published rubrics.
Read-only lookup of tested agent tools and MCP servers: scores, test evidence, deprecation.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables to extract project handover evidence and check material completeness against requirements without making approval decisions.-
- FlicenseNot gradedqualityDmaintenanceEnables spec-driven development acceptance gate with structured receipts, audit logs, and reviewer-ready evidence.-
- AlicenseNot gradedqualityBmaintenanceEnables deliverable conformance and evidence-chain checks by turning requirements into executable specs, validating numbers against a provenance ledger, and auditing PDF/OOXML metadata and archive manifests.38 npm1MIT
- FlicenseNot gradedqualityCmaintenanceEnables users to check whether procedures are current and whether actions have the stored evidence needed for human review, returning status, citations, and blockers through read-only MCP tools while always requiring human review.-