dod-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DOD_DIR | No | DoD folder. Default is `<repo>/dod` locally and `/dod` in the container. Without DOD_DIR the server serves the fictional example in `dod/`. | <repo>/dod / /dod |
| DOD_PORT | No | HTTPS port. No default for local stdio; `8443` in the container. | 8443 |
| DOD_DATABASE | No | Version history database. Default is `sqlite:<repo>/local/dod.sqlite` locally and `sqlite:/data/dod.sqlite` in the container; `sqlite::memory:` for tests. | sqlite:<repo>/local/dod.sqlite / sqlite:/data/dod.sqlite |
| DOD_TRANSPORT | No | Transport. Default is `stdio` locally and `https` in the container. | stdio / https |
| DOD_TOKEN_FILE | No | File containing bearer tokens, one per line, at least 32 characters. Default in the container is `/run/secrets/dod_tokens`. | /run/secrets/dod_tokens |
| DOD_TLS_KEY_FILE | No | PEM key file for HTTPS. Default in the container is `/run/secrets/tls_key`. | /run/secrets/tls_key |
| DOD_ALLOWED_HOSTS | No | Accepted `Host` values. Default in the container is `localhost,127.0.0.1`. | localhost,127.0.0.1 |
| DOD_TLS_CERT_FILE | No | PEM certificate file for HTTPS. Default in the container is `/run/secrets/tls_cert`. | /run/secrets/tls_cert |
| DOD_ALLOWED_ORIGINS | No | Accepted `Origin` values; empty rejects every browser request. Default in the container is empty. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Serves a team's Definition of Done: a base and one file per task type. Order: get_dod with the ticket's ticket_type and labels; fetch each evidence criterion's value with the tools it names and pass it unchanged to check_dod; answer needs_judgment criteria with rubric://dod/{type}, quoting the material. The server reports met / not_met / needs_judgment per criterion; your assessment is plausible / doubtful; whether an item is done is the team's decision, never yours. Never invent evidence and never confirm an attestation yourself. lint_acceptance_criteria checks acceptance criteria against template://{type}. diff_dod compares versions of a type or the base for DoD reviews. The prompt done_check runs the whole check. All tools are read-only.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
| completions | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_dodA | 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. |
| check_dodA | 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. |
| lint_acceptance_criteriaA | 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. |
| diff_dodA | 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. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| done_check | Check an item against its Definition of Done: determine the type, collect evidence with your other servers, run check_dod, answer the judgment questions with the rubric, and report per criterion. Writes nothing; the team decides whether the item is done. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| dod-types | Overview of the Definition of Done: the base, the ticket type and label mapping, and every task type with its version label, number of criteria, validity and errors with file and line. |
| DoD dokument | The Definition of Done of one task type: base and type merged, every criterion with origin (base or the type), file, line and check kind (evidence, judgment, attestation); the rules for acceptance criteria. An invalid type file shows its errors instead. |
| DoD kundenanfrage | The Definition of Done of one task type: base and type merged, every criterion with origin (base or the type), file, line and check kind (evidence, judgment, attestation); the rules for acceptance criteria. An invalid type file shows its errors instead. |
| DoD software-dev | The Definition of Done of one task type: base and type merged, every criterion with origin (base or the type), file, line and check kind (evidence, judgment, attestation); the rules for acceptance criteria. An invalid type file shows its errors instead. |
| template dokument | How acceptance criteria for this task type are written, and which rules lint_acceptance_criteria applies to them. |
| template kundenanfrage | How acceptance criteria for this task type are written, and which rules lint_acceptance_criteria applies to them. |
| template software-dev | How acceptance criteria for this task type are written, and which rules lint_acceptance_criteria applies to them. |
| rubric dokument | The judgment criteria of a task type with their questions and the standards for plausible and doubtful; which criteria a named role confirms instead. |
| rubric kundenanfrage | The judgment criteria of a task type with their questions and the standards for plausible and doubtful; which criteria a named role confirms instead. |
| rubric software-dev | The judgment criteria of a task type with their questions and the standards for plausible and doubtful; which criteria a named role confirms instead. |
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.