santismm-knowledge-mcp
MCP server for the Santismm Knowledge Platform — harness engineering, agentic AI patterns, architectures and AI governance. Generated from santismm.com.
Documentation
santismm-knowledge-mcp
> MCP server for the Santismm Knowledge Platform — five core knowledge domains,
> first-party essays, Homeric Atlas datasets and epistemic claims.
This repository is generated from the platform at santismm.com.
Do not edit it by hand; changes are overwritten on the next sync. Corrections go
through the site.
Use it without installing anything
The same server is hosted, so most people want the endpoint rather than this
repository:
{ "mcpServers": { "santismm-knowledge": { "type": "http", "url": "https://santismm.com/mcp" } } }Docs: https://santismm.com/en/mcp · Registry: `com.santismm/knowledge`
Where this server is listed
Derived from the same list the site renders on its own MCP page, so a registry
added there is linked from here too — and a directory that checks for a backlink
before ranking a server finds one without anybody remembering to add it.
Run it locally (stdio)
npm ci && npm run build && npm startThe core corpus ships in `content/` and is read from disk, so its tools work
offline. The three federated Article tools read the canonical Articles API over
HTTPS. Point the core corpus elsewhere with `SANTISMM_CONTENT_DIR`.
Install from npm
npx santismm-knowledge-mcpOr in an MCP client config (stdio):
{ "mcpServers": { "santismm-knowledge": { "command": "npx", "args": ["santismm-knowledge-mcp"] } } }The npm package carries the corpus frozen at publish time; this repository
and the hosted endpoint update continuously. When freshness matters, prefer
the endpoint.
Install from PyPI (Python)
uvx santismm-knowledge-mcpThe Python package (in `python/`) is a **zero-dependency stdio
proxy to the hosted endpoint** — it ships no corpus, so it is always fresh.
{ "mcpServers": { "santismm-knowledge": { "command": "uvx", "args": ["santismm-knowledge-mcp"] } } }Licences
Code is MIT (LICENSE); the knowledge corpus in `content/` is
CC BY 4.0 (content/LICENSE) — two licences because CC BY
is not a software licence and MIT is not a content licence.
What it exposes
30 read-only tools over knowledge, patterns, architectures, governance, the
Harness Engineering Handbook and first-party Articles, each declaring an
`outputSchema` and returning validated `structuredContent`. Every tool is
annotated `readOnlyHint: true`, `destructiveHint: false` and
`idempotentHint: true`. The three federated Article tools declare
`openWorldHint: true`; local-corpus tools remain `false`.
Content in seven languages (en/es/pt/fr/de/ja/zh).
Licence
Code: MIT. Content: Content © Santiago Santa María Morales, licensed CC BY 4.0. Attribution required: credit the author and link the canonical URL. (CC-BY-4.0, https://creativecommons.org/licenses/by/4.0/).
Frequently asked questions
What is santismm-knowledge-mcp?
santismm-knowledge-mcp is MCP server for the Santismm Knowledge Platform — harness engineering, agentic AI patterns, architectures and AI governance. Generated from santismm.com.
How do I install santismm-knowledge-mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is santismm-knowledge-mcp open source?
Yes — it is hosted on GitHub at https://github.com/santismm/santismm-knowledge-mcp.
Related MCP tools
A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.
The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.
MCP Aggregator, Orchestrator, Middleware, Gateway in one docker
A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Model Context Protocol (MCP) and enabling cross-vendor LLM API orchestration.
Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Windsurf, Gemini CLI, Antigravity, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Copilot, Kiro, OpenCode, and Trae.
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP