Model Context Protocol

Query this corpus natively from any AI agent

The Santismm Knowledge Platform is exposed as a public MCP server over Streamable HTTP. Point any MCP-capable client at the endpoint below to read the same knowledge units, Enterprise AI patterns, reference architectures and governance units that power this site — structured, with Evidence-First provenance.

https://santismm.com/mcp
Transport

Streamable HTTP (JSON-RPC)

Stateless Streamable HTTP — no SSE session and no API key. Send JSON-RPC requests (initialize, tools/list, tools/call) to https://santismm.com/mcp with Accept: application/json, text/event-stream.

Every tool declares an outputSchema and returns validated structuredContent, so results arrive as typed data — the serialized JSON stays in content for older clients. CORS is open, so browser-based MCP clients work too. Search covers all three languages, ignores accents and ranks hits by relevance.

get_overview

Get the corpus map: the available domains (knowledge, patterns, architectures, governance and the Harness Engineering Handbook) and how many units each has. A good first call.

list_knowledge

List all knowledge units (concepts on agentic & enterprise AI) with slug, category, title, summary and Evidence-First provenance.

get_knowledge

Get one knowledge unit by slug. Returns the full entry, or a single-locale body if locale is given.

list_patterns

List all Enterprise AI patterns (reusable agentic design patterns) with slug, category, name, summary and provenance.

get_pattern

Get one Enterprise AI pattern by slug (includes problem, solution, KPIs, failure modes, lessons).

list_architectures

List all reference architectures (end-to-end enterprise agentic blueprints) with id, slug, category, name, summary and provenance.

get_architecture

Get one reference architecture by slug (includes the request flow, reference scenario, KPIs, cost & scaling, and the patterns/knowledge it composes).

list_governance

List all AI governance units (regulations, standards, frameworks, playbooks — EU AI Act, ISO 42001, NIST AI RMF, agentic checklist) with id, slug, category, name and summary.

get_governance

Get one AI governance unit by slug (includes scope, key requirements, implementable controls, a checklist and common pitfalls).

list_handbook

List the Harness Engineering Handbook chapters (HRN-001…): the canonical long-form corpus on harness engineering — definition, history, taxonomy, principles, memory, observability, evaluation, governance, planning, orchestration, security, case studies, glossary and bibliography.

get_handbook

Get one Harness Engineering Handbook chapter, by id (e.g. 'HRN-001') or slug. Returns the full Markdown body plus its provenance and related ids.

search

Ranked keyword search across the whole corpus (knowledge, patterns, architectures, governance and the handbook). Matches every language and ignores accents, so query in the user's own words. Each hit carries a relevance score and the fields it matched; follow up with the matching get_* tool for full detail.

get_related

Traverse the knowledge graph: given a unit, return its neighbours — the units it links to (outgoing) and the units that reference it (incoming), each with the relationship type.

Client config

Add it to your MCP client

Most MCP clients (Claude Desktop, IDE extensions, custom agents) accept an HTTP MCP server in their config. Paste:

{
  "mcpServers": {
    "santismm-knowledge": {
      "type": "http",
      "url": "https://santismm.com/mcp"
    }
  }
}

Four domains: knowledge, patterns, architectures, governance — start with get_overview.

Traverse links with get_related, the same graph behind /api/graph.json.

Every unit carries Evidence-First provenance (evidence level, confidence, source types).