DecisionPen MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DP_API_BASE | Yes | Base URL of your DecisionPen host (e.g., https://YOUR_DECISIONPEN_HOST). | |
| DP_MCP_MODE | Yes | Mode for the trust ladder: cite_only or propose. Confirmed writes require human approval in the Inbox. | |
| DP_API_TOKEN | Yes | DecisionPen Edge API token (e.g., dp_edge_…) or session JWT for trials. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_sourcesA | List folders and files under the allowlisted S3 prefix. path: optional subfolder relative to DP_S3_PREFIX (or absolute key under it). next_token: pagination token from a previous list_sources call. |
| search_docsA | Search object keys/names under the allowlisted prefix (substring match, case-insensitive). query: text to match in the object key. path: optional subfolder to search within. max_results: optional cap (defaults to DP_MCP_MAX_SEARCH_RESULTS). |
| get_documentA | Fetch one object from the allowlisted S3 prefix. Returns provenance + text when extractable. Does not persist into DecisionPen (mode=cite_only|propose|persist_approved — MCP itself never Confirmed-writes). item_id: full S3 object key (from list_sources / search_docs). include_text: when true, attempt text extraction for cite-only use. |
| propose_enrichmentA | Download the object at the edge and push bytes + provenance to DecisionPen (Insights Inbox). Requires DP_MCP_MODE=propose|persist_approved, DP_API_TOKEN (Edge API token preferred), DP_API_BASE. No S3 keys are sent to DecisionPen. Nothing is Confirmed on the map until a human approves in the Inbox. item_id: S3 object key under the allowlisted prefix. |
| run_syncB | Run edge sync: list allowlisted S3 prefix, push new/modified files to DecisionPen. dry_run: report candidates without download/push. Requires DP_MCP_MODE=propose|persist_approved and DP_API_TOKEN. |
| get_enrichment_jobB | Poll DecisionPen enrichment job status. Review-ready when status=completed and a preview is present. Same auth caps as propose_enrichment. |
| rerun_enrichment_jobA | Re-queue a failed or completed application_enrichment job (same sources). Blocked while pending/queued/running. Suggestions are replaced; map items stay. |
| describe_context_modelA | How to use DecisionPen as a Context Engine: Confirmed map vs evidence notes, capability-first landscape workflow, and recommended tool call order. Call once at the start of an EA Q&A session. |
| search_entitiesA | Search Confirmed map entities by name/description. For landscape questions (e.g. what supports clinical trials), search capability/process types FIRST, then follow relationships to applications. query: search text. entity_type: optional type filter (capability, process, application, …). limit: max results. |
| get_entityA | Fetch one Confirmed map entity (description, aliases, custom_attributes). Optionally include relationships / related entity stubs. entity_id: from search_entities. |
| get_entity_relationshipsA | Confirmed map relationships for an entity (incoming/outgoing endpoints). Label these as Confirmed — not evidence-only mentions. entity_id: from search_entities / get_entity. |
| get_entity_evidenceA | Unstructured evidence pack for one entity: linked fragments + summary_node. Use after resolving CTMS/EDC/any app id. Cite fragment_id and source_title. Do not promote note-only integrations to Confirmed map edges. |
| search_evidenceA | Semantic search over DecisionPen evidence fragments (no generative answer). Prefer passing entity_id to scope to one application/capability. Prefer get_entity_evidence for the full linked pack of one entity. query: search text. limit: max fragments (1–50). entity_id: strongly recommended — filter to fragments linked to that entity. |
| get_relationship_summaryA | Cheap Confirmed relationship counts by type and direction (incoming|outgoing). Use before deep get_entity_relationships when exploring a busy entity. |
| list_entity_typesA | List valid map entity types for search_entities entity_type filters (capability, application, process, …). |
| batch_get_entitiesA | Hydrate many entity ids (e.g. peers from relationships). entity_ids: comma-separated ids (max 50). |
| ask_decisionpenA | LAST RESORT narrative Ask over DecisionPen (server-side agent + LLM). Prefer structured Context tools first: search_entities → relationships → get_entity_evidence / search_evidence. Use this only when those are insufficient. query: natural-language question. thread_id: optional prior thread_id to continue a conversation. skill_id: optional skill from list_ask_skills. |
| list_ask_skillsA | List user-invocable DecisionPen Ask skills (for ask_decisionpen skill_id only). Prefer Context tools over Ask for catalog Q&A. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 18 tools
Tools split into clearly described workflows (S3 source browsing/ingestion vs. Confirmed-map context vs. Ask fallback), and most boundaries are explicit in the descriptions. A few near-overlaps exist, notably search_docs vs. list_sources, search_evidence vs. get_entity_evidence, and get_relationship_summary vs. get_entity_relationships, but the descriptions provide enough guidance to choose correctly.
All tools use snake_case with a predictable verb_noun or verb_resource construction (get_, list_, search_, propose_, run_, rerun_, describe_, ask_). The batch_get_entities prefix is a minor variation but remains clear and consistent with the rest.
Eighteen tools is slightly above the typical sweet spot, but the surface covers two coherent sub-domains (S3 ingestion and DecisionPen context retrieval), and each tool has a distinct role. A few tools (e.g., list_ask_skills, describe_context_model) feel peripheral but still earn their place.
The surface covers source discovery/fetch/propose/sync with job polling, full entity search/hydration/relationship/evidence flows, and an Ask fallback. Minor gaps remain around enrichment job listing/history and explicit approval workflows, but these appear intentionally human-gated rather than missing agent operations.