# Santismm Knowledge — Harness Engineering, Agentic AI & Governance (remote · santismm.com)

Search harness engineering, agentic AI patterns, architectures, governance and agent taxonomy.

- Trust score: 73/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `santismm.com`: 73/100 (this document), [markdown](https://verifymcp.io/servers/com-santismm-knowledge/santismm.md), [page](https://verifymcp.io/servers/com-santismm-knowledge/santismm)

## Channel facts

- Endpoint: `https://santismm.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 1200 tokens (~92/item across 13 items; 13 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 7/100
  - Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 95% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### Claude

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

### Codex

```toml
[mcp_servers.com-santismm-knowledge]
url = "https://santismm.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-santismm-knowledge": {
      "type": "remote",
      "url": "https://santismm.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-santismm-knowledge --url https://santismm.com/mcp --transport streamable-http
```

### Hermes

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

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 73, +7)

- [security improvement] Authorization: unverified → partial
- [functional regression] Schema quality: 74 → 92
- [functional improvement] Stability: unverified → 0.03
- [functional] MCP protocol: Implements a current MCP spec version (2026-07-28).
- [functional] MCP protocol version: 2025-11-25 → 2026-07-28

### 2026-08-01 (score 66)

First indexed and scored.

## MCP tools (13)

### `get_overview` (~79 tokens)

Corpus Overview — Start Here

Get the corpus map — start here. Returns every domain (knowledge, patterns, architectures, governance and the Harness Engineering Handbook) with what it holds, the categories inside it, which tool retrieves a unit and what identifier that tool expects, plus the languages, licence and bulk-ingest URLs. One call is enough to know exactly where to go next.

Output parameters:

- `bulk` (object)
- `domains` (array)
- `license` (string)
- `license_spdx` (string): SPDX id — check this, not the prose.
- `license_url` (string)
- `locales` (array)
- `next` (string)
- `site` (string)
- `source` (string)
- `total` (number)

### `list_knowledge` (~74 tokens)

List Agentic AI Knowledge Units

List all knowledge units (concepts on agentic & enterprise AI) with slug, category, title, summary and Evidence-First provenance. Use this to browse the domain; use `search` when you have a question rather than a slug.

Input parameters:

- `locale` (string): Language of the returned body. Default: en.

Output parameters:

- `count` (number)
- `results` (array)

### `get_knowledge` (~85 tokens)

Get an Agentic AI Knowledge Unit

Get one knowledge unit by slug. Returns the full entry, or a single-locale body if locale is given. Use this once `search` or `list_knowledge` has given you a slug.

Input parameters:

- `locale` (string): Language of the returned body. Default: en.
- `slug` (string, required): Knowledge unit slug, e.g. 'harness-engineering'.

Output parameters:

- `api_url` (string)
- `body`
- `canonical_url` (string)
- `category` (string)
- `domain` (string)
- `evidence` (object): Evidence-First provenance: weight claims by this.
- `fallback` (boolean)
- `featured` (boolean)
- `frameworks` (array)
- `id` (string)
- `knowledge` (array)
- `locale` (string)
- `locales` (object)
- `name` (string)
- `patterns` (array)
- `references` (array)
- `related` (array)
- `requested_locale` (string)
- `resolved_locale` (string)
- `slug` (string)
- `status` (string)
- `summary` (string)
- `tags` (array)
- `technologies` (array)
- `updated` (string)
- `version` (string)

### `list_patterns` (~71 tokens)

List Enterprise AI Patterns

List all Enterprise AI patterns (reusable agentic design patterns) with slug, category, name, summary and provenance. Use this to browse the catalogue; use `search` when you are looking for a pattern that solves a problem.

Input parameters:

- `locale` (string): Language of the returned body. Default: en.

Output parameters:

- `count` (number)
- `results` (array)

### `get_pattern` (~81 tokens)

Get an Enterprise AI Pattern

Get one Enterprise AI pattern by slug (includes problem, solution, KPIs, failure modes, lessons). Use this once `search` or `list_patterns` has given you a slug.

Input parameters:

- `locale` (string): Language of the returned body. Default: en.
- `slug` (string, required): Pattern slug, e.g. 'human-approval-gate'.

Output parameters:

- `api_url` (string)
- `body`
- `canonical_url` (string)
- `category` (string)
- `domain` (string)
- `evidence` (object): Evidence-First provenance: weight claims by this.
- `fallback` (boolean)
- `featured` (boolean)
- `frameworks` (array)
- `id` (string)
- `knowledge` (array)
- `locale` (string)
- `locales` (object)
- `name` (string)
- `patterns` (array)
- `references` (array)
- `related` (array)
- `requested_locale` (string)
- `resolved_locale` (string)
- `slug` (string)
- `status` (string)
- `summary` (string)
- `tags` (array)
- `technologies` (array)
- `updated` (string)
- `version` (string)

### `list_architectures` (~76 tokens)

List Agentic Reference Architectures

List all reference architectures (end-to-end enterprise agentic blueprints) with id, slug, category, name, summary and provenance. Use this to browse the blueprints; use `search` when you have a use case rather than a name.

Input parameters:

- `locale` (string): Language of the returned body. Default: en.

Output parameters:

- `count` (number)
- `results` (array)

### `get_architecture` (~92 tokens)

Get an Agentic Reference Architecture

Get one reference architecture by slug (includes the request flow, reference scenario, KPIs, cost & scaling, and the patterns/knowledge it composes). Use this once `search` or `list_architectures` has given you a slug.

Input parameters:

- `locale` (string): Language of the returned body. Default: en.
- `slug` (string, required): Architecture slug, e.g. 'customer-service-agent'.

Output parameters:

- `api_url` (string)
- `body`
- `canonical_url` (string)
- `category` (string)
- `domain` (string)
- `evidence` (object): Evidence-First provenance: weight claims by this.
- `fallback` (boolean)
- `featured` (boolean)
- `frameworks` (array)
- `id` (string)
- `knowledge` (array)
- `locale` (string)
- `locales` (object)
- `name` (string)
- `patterns` (array)
- `references` (array)
- `related` (array)
- `requested_locale` (string)
- `resolved_locale` (string)
- `slug` (string)
- `status` (string)
- `summary` (string)
- `tags` (array)
- `technologies` (array)
- `updated` (string)
- `version` (string)

### `list_governance` (~91 tokens)

List AI Governance Units

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. Use this to browse the regulations and standards; use `search` for an obligation or control.

Input parameters:

- `locale` (string): Language of the returned body. Default: en.

Output parameters:

- `count` (number)
- `results` (array)

### `get_governance` (~87 tokens)

Get an AI Governance Unit

Get one AI governance unit by slug (includes scope, key requirements, implementable controls, a checklist and common pitfalls). Use this once `search` or `list_governance` has given you a slug.

Input parameters:

- `locale` (string): Language of the returned body. Default: en.
- `slug` (string, required): Governance unit slug, e.g. 'eu-ai-act'.

Output parameters:

- `api_url` (string)
- `body`
- `canonical_url` (string)
- `category` (string)
- `domain` (string)
- `evidence` (object): Evidence-First provenance: weight claims by this.
- `fallback` (boolean)
- `featured` (boolean)
- `frameworks` (array)
- `id` (string)
- `knowledge` (array)
- `locale` (string)
- `locales` (object)
- `name` (string)
- `patterns` (array)
- `references` (array)
- `related` (array)
- `requested_locale` (string)
- `resolved_locale` (string)
- `slug` (string)
- `status` (string)
- `summary` (string)
- `tags` (array)
- `technologies` (array)
- `updated` (string)
- `version` (string)

### `list_handbook` (~100 tokens)

List Harness Engineering Handbook Chapters

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. Use this to see the chapter map; use `search` when you have a topic rather than a chapter.

Input parameters:

- `locale` (string): Language of the returned body. Default: en.

Output parameters:

- `count` (number)
- `results` (array)

### `get_handbook` (~96 tokens)

Get a Harness Engineering Handbook Chapter

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. Use this once `search` or `list_handbook` has given you an id.

Input parameters:

- `id` (string, required): Chapter id like 'HRN-001', or its slug.
- `locale` (string): Language of the returned body. Default: en.

Output parameters:

- `api_url` (string)
- `body` (string): Full Markdown body of the chapter.
- `canonical_url` (string)
- `category` (string)
- `domain` (string)
- `evidence` (object): Evidence-First provenance: weight claims by this.
- `fallback` (boolean): True when the body is not in the requested locale.
- `featured` (boolean)
- `frameworks` (array)
- `id` (string)
- `knowledge` (array)
- `locale` (string)
- `locales` (object)
- `name` (string)
- `patterns` (array)
- `references` (array)
- `related` (array)
- `requested_locale` (string): The locale that was asked for.
- `resolved_locale` (string): The locale actually returned — the handbook is authored in English only.
- `slug` (string)
- `status` (string)
- `summary` (string)
- `tags` (array)
- `technologies` (array)
- `updated` (string)
- `version` (string)

### `search` (~156 tokens)

Search Harness Engineering & Agentic AI

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. Use this before any `get_*` tool whenever you have a question rather than an identifier.

Input parameters:

- `domains` (array): Restrict to these domains. Omit to search everything, including the handbook.
- `limit` (integer): Max results (default 20).
- `locale` (string): Language of the returned body. Default: en.
- `query` (string, required): Keyword or phrase to search for, in any of en/es/pt.

Output parameters:

- `count` (number)
- `query` (string)
- `results` (array)

### `get_related` (~112 tokens)

Traverse the Knowledge Graph

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. Use this after a `get_*` call to widen an answer with adjacent units.

Input parameters:

- `domain` (string, required)
- `locale` (string): Language of the returned body. Default: en.
- `slug` (string, required): Slug of the unit to start from (or an HRN id when domain is 'handbook').

Output parameters:

- `incoming` (array)
- `outgoing` (array)
- `unit` (object)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-santismm-knowledge/santismm#diagnostics

## Score history

- 2026-08-03: 73
- 2026-08-02: 73
- 2026-08-01: 66

## Links

- Remote endpoint: https://santismm.com/mcp
- Repository: https://github.com/santismm/santismm-knowledge-mcp
- Website: https://santismm.com/en/mcp
- Changelog RSS feed: https://verifymcp.io/servers/com-santismm-knowledge/santismm/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-santismm-knowledge/santismm/changelog.json
- HTML version of this page: https://verifymcp.io/servers/com-santismm-knowledge/santismm