mcp
com.decisionpen/mcp
Architecture context for Claude and Cursor: estate graph, evidence, standards; ADRs back for review.
Documentation
DecisionPen Context Engine (MCP)
Works with Claude Desktop, Cursor, and any Model Context Protocol (MCP) client.
DecisionPen is the Context of Record for IT architecture — institutional memory of how the enterprise is built and why. Agents help keep it current. Humans review what becomes trusted.
This repository ships the Context Engine: an MCP server that connects Claude, Cursor, and other agents to that plane. Three common jobs:
- Rapid discovery — connect an allowlisted S3 document corpus; DecisionPen proposes LeanIX-aligned structure and keeps document evidence; CMDB-seeded entities get enriched instead of duplicated.
- Claude — deep research over the Context of Record before important decisions (natural trial path).
- Cursor / agentic SDLC — pull approved patterns and standards while building; publish ADRs and design notes back for human curation.
Agents can read the Enterprise Knowledge Graph, evidence, decisions, and context surfaces; read allowlisted document stores; and publish requirements, ADRs, and notes back. MCP never Confirmed-writes the architecture map. Humans approve what joins the graph.
Hosted remote endpoint (registry / cloud clients): https://mcp.decisionpen.com/mcp with Authorization: Bearer dp_edge_….
| Guide | What it covers |
|---|---|
| This page | What DecisionPen is, what MCP does, and the tools in plain English |
| CONNECT.md | Connect Claude or Cursor (including Edge API tokens) |
| CONTEXT.md | Tool recipes for research and solution design |
| SYNC.md | S3 allowlist sync runbook |
| Product docs | decisionpen.com/docs/context-engine-mcp |
Marketing setup guides (SEO / step-by-step):
Why MCP matters here
Enterprise discovery, institutional memory, agentic SDLC, agentic solution architecture, and living enterprise architecture all need the same harnessed context. Without it, agents invent topology or burn tokens re-reading the same HLDs.
MCP is the two-way door:
- Read — graph, evidence, decisions, open estate changes
- Read documents — allowlisted object store (optional S3)
- Publish —
submit_document/propose_enrichment→ Inbox → human approve
Same plane as built-in Enterprise Ask. Two doors; one Context of Record.
Tools in plain English
Orient
| Tool | What it does |
|---|---|
describe_context_model | Once per session: how the plane is layered (map, evidence, surfaces, Inbox). |
Read the Enterprise Knowledge Graph
| Tool | What it does |
|---|---|
search_entities | Find applications, capabilities, etc. by name. |
get_entity | Description, aliases, attributes for one entity. |
get_entity_relationships | Confirmed links on the map. |
get_relationship_summary | Quick counts by type/direction. |
list_entity_types / batch_get_entities | Filters and hydrate many entities. |
Read institutional memory
| Tool | What it does |
|---|---|
get_entity_evidence | Documents and notes bound to an entity (current by default). |
search_evidence | Semantic search; pass entity_id or a knowledge surface when you can. |
list_derived_decisions | Living architecture-decision / ADR cards on an entity. |
list_entity_changes | Open or recent estate changes (e.g. pending tech replace). |
list_context_surfaces / get_surface_evidence | Shared patterns, principles, security standards. |
Read document repositories (optional S3)
| Tool | What it does |
|---|---|
list_sources | Browse folders/files under the allowlisted prefix. |
search_docs | Search object keys. |
get_document | Fetch one object to cite (does not save into DecisionPen). |
propose_enrichment | Push an S3 object into DecisionPen for Inbox review. |
run_sync | Sync new/changed objects (also available as CLI). |
get_enrichment_job / rerun_enrichment_job | Poll or retry enrichment jobs. |
Publish (agents write; humans approve)
| Tool | What it does |
|---|---|
submit_document | Push UTF-8 text onto an entity or knowledge surface (no S3 required). |
propose_enrichment | Same Inbox path from an S3 object. |
Requires DP_MCP_MODE=propose (or persist_approved). Nothing becomes Confirmed on the map until a steward accepts it in Inbox.
Ask (last resort)
| Tool | What it does |
|---|---|
ask_decisionpen | Server-side Ask with citations. Prefer structured tools above so the agent owns the research plan. |
list_ask_skills | Optional skill ids for Ask. |
Modes
DP_MCP_MODE | Behaviour |
|---|---|
cite_only (default) | Read / cite. No push into DecisionPen. |
propose | Agents can submit documents and propose enrichment (Inbox). |
persist_approved | Advanced; still does not Confirmed-write the map from MCP. |
Quick start
- Create an Edge API token: DecisionPen → Admin → Security & audit → Edge API tokens → Create.
- Follow CONNECT.md for Claude Desktop or Cursor.
- For document repositories, follow SYNC.md and the S3 docs page.
git clone https://github.com/DecisionPen/decisionpen-mcp.git
cd decisionpen-mcp
python -m venv .venv
source .venv/bin/activate # Windows: .\.venv\Scripts\Activate.ps1
pip install -e .
cp examples/.env.mcp.example .env.mcp
# set DP_API_BASE + DP_API_TOKEN
Security defaults
- DecisionPen does not store customer S3 keys on the edge push path. Credentials stay on the edge (your laptop, VPC, or container).
- Prefix allowlisting, audit log, and rate limits apply.
- Tokens are hashed at rest; revoke anytime in Admin.
Related product story
No installation packages available.