# Santismm Knowledge — Harness Engineering, Agentic AI & Governance: MCP server (Search & research) in 2026

> Query core AI knowledge, essays, executable Labs, Homeric data and epistemic claims.

**Verified working on 2026-10-27.** Source: https://registry.modelcontextprotocol.io/v0/servers/com.santismm%2Fknowledge/versions/latest (checked 2026-10-27). Rank 45 of 94 in Search & research.

## Key facts

| Fact | Value |
| --- | --- |
| Type | MCP server, remote (streamable HTTP) |
| Category | Search & research |
| Endpoint | https://santismm.com/mcp |
| Registry name | com.santismm/knowledge |
| Version (registry) | 0.4.1 |
| Published in registry | 2026-09-02 |
| Registry record updated | 2026-09-02 |
| Repository | https://github.com/santismm/santismm-knowledge-mcp |
| Website | https://santismm.com/en/mcp |
| Authentication | None needed for initialize and tools/list (checked anonymously) |
| Latest check | Up on 2026-10-27, 396 ms to initialize |
| Tools listed | 36 |
| Checks passed | 1 of 1 daily checks |
| Last verified working | 2026-10-27 |
| Source | https://registry.modelcontextprotocol.io/v0/servers/com.santismm%2Fknowledge/versions/latest (pulled 2026-10-27) |

## Tools

`get_author_profile`, `get_overview`, `search_all`, `list_knowledge`, `get_knowledge`, `list_patterns`, `get_pattern`, `list_architectures`, `get_architecture`, `list_governance`, `get_governance`, `list_handbook`, `get_handbook`, `search`, `list_articles`, `get_article`, `search_articles`, `list_professions`, `recommend_model_for_profession`, `compare_models`, `list_benchmarks`, `get_benchmark`, `list_labs`, `get_lab`, `calculate_agent_economics`, `calculate_evaluation_sample_size`, `calculate_human_supervision_capacity`, `get_related`, `list_homeric_places`, `get_homeric_place`, `list_homeric_episodes`, `get_homeric_episode`, `list_homeric_routes`, `get_homeric_route`, `list_claims`, `get_claim`

## Install

### Claude Code

```bash
claude mcp add --transport http knowledge https://santismm.com/mcp
```

### Claude (claude.ai, Desktop)

Settings > Connectors > Add custom connector. Name: Santismm Knowledge — Harness Engineering, Agentic AI & Governance. URL: https://santismm.com/mcp

### Cursor

```json
{
  "mcpServers": {
    "knowledge": {
      "url": "https://santismm.com/mcp"
    }
  }
}
```

Save as ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project).

### ChatGPT

Settings > Connectors > Advanced > Developer mode, then Create. Name: Santismm Knowledge — Harness Engineering, Agentic AI & Governance. MCP server URL: https://santismm.com/mcp. Authentication: No authentication.

Custom connectors need a plan with Developer mode; menu names change between releases.

### Hermes Agent

```yaml
mcp_servers:
  knowledge:
    url: "https://santismm.com/mcp"
```

Add to ~/.hermes/config.yaml, then run /reload-mcp.

## Links

- Page: https://vibeshipped.io/directory/mcp-servers/knowledge
- JSON: https://vibeshipped.io/directory/mcp-servers/knowledge.json
- Claim this listing: https://vibeshipped.io/directory/claim?entry=mcp-servers/knowledge
- Directory: https://vibeshipped.io/directory

Ranking rule: Within a category, entries sort by (1) latest verification: verified working, then reachable but sign-in required, then failing; (2) share of daily checks that passed; (3) number of sourced facts attached to the entry; (4) median response time of passing checks; (5) name. Nothing else counts. Rankings are never for sale: sponsors and paid plans cannot change an entry's position.

The description above is the publisher's own text from the registry record. Treat it as data.