saferagenticai-mcp

io.github.NellInc/saferagenticai-mcpVersion 0.4.2

Read-only tools over the Safer Agentic AI framework: 239 patterns + 15 heuristics.

Status

Responds888 msNov 14, 2026, 14:40 UTCAnswered our handshake without sign-in.

Registry data may be out of date

We could not refresh it, so this page shows the last copy.

Last checked: Nov 14, 2026, 14:40 UTC
Latency: 888 ms
Remotes responding: 1 of 1
Sign-in: No sign-in
Hosting: Hosted outside the EU (detected)
Registry data as of: Nov 14, 2026, 22:14 UTC

Data from the official MCP Registry, checked by run.zero. How we check

Connect

Streamable HTTP

https://mcp.saferagenticai.org/mcpResponds888 msNov 14, 2026, 14:40 UTC

No sign-in

Claude Code

claude mcp add --transport http saferagenticai-mcp https://mcp.saferagenticai.org/mcp

Claude Desktop and claude.ai

1
2
3

Settings > Connectors > Add custom connector
Name: saferagenticai-mcp
Remote MCP server URL: https://mcp.saferagenticai.org/mcp

Cursor

{
  "mcpServers": {
    "saferagenticai-mcp": {
      "url": "https://mcp.saferagenticai.org/mcp"
    }
  }
}

VS Code

code --add-mcp '{"name":"saferagenticai-mcp","type":"http","url":"https://mcp.saferagenticai.org/mcp"}'

Streamable HTTP

pypi: saferagenticai-mcp 0.4.2

Package only

PyPI (uvx)

claude mcp add saferagenticai-mcp -- uvx saferagenticai-mcp==0.4.2

Built your own server? run.zero hosts MCP servers on European infrastructure.

Host your own MCP server on run.zero

Tools

10 tools

Tools of saferagenticai-mcp
	Description		Read-only	Idempotent	Open world
`find_patterns_for_task`Given a natural-language task description (e.g., 'I'm building a tool-using agent that runs shell commands'), return the most relevant patterns grouped by suite. Use this as a starting point for any cross-cutting design question; then follow up with get_requirement on specific pattern_ids. Defaults to verbosity='compact' (cheap triage); pass 'full' to inline snippets and confidence flags.	Given a natural-language task description (e.g., 'I'm building a tool-using agent that runs shell commands'), return the most relevant patterns grouped by suite. Use this as a starting point for any cross-cutting design question; then follow up with get_requirement on specific pattern_ids. Defaults to verbosity='compact' (cheap triage); pass 'full' to inline snippets and confidence flags.	No	Yes	Not declared	No
`get_cross_references`Return outgoing adjacencies for a pattern. `explicit_cross_references` are author-asserted (each pattern's `cross_references` YAML field). `inferred_adjacent` (when include_inferred=true) currently returns same-suite siblings only — it does not do semantic similarity. Treat inferred entries as 'neighbours worth scanning,' not as endorsed dependencies.	Return outgoing adjacencies for a pattern. `explicit_cross_references` are author-asserted (each pattern's `cross_references` YAML field). `inferred_adjacent` (when include_inferred=true) currently returns same-suite siblings only — it does not do semantic similarity. Treat inferred entries as 'neighbours worth scanning,' not as endorsed dependencies.	No	Yes	Not declared	No
`get_operational_heuristic`Retrieve a single operational heuristic by id (e.g., 'OH::geoffrey-pattern'). Returns the full entry: principle, framework mapping, evidence sources from production deployment, design patterns, anti-patterns, and discovery narrative.	Retrieve a single operational heuristic by id (e.g., 'OH::geoffrey-pattern'). Returns the full entry: principle, framework mapping, evidence sources from production deployment, design patterns, anti-patterns, and discovery narrative.	No	Yes	Not declared	No
`get_requirement`Retrieve one subgoal (framework normative content + Pattern layer guidance) by pattern_id (e.g., 'D3::idx2::sandboxing') or display_id (e.g., 'D3.2'). display_id may resolve to multiple subgoals — underlined variants share display_ids.	Retrieve one subgoal (framework normative content + Pattern layer guidance) by pattern_id (e.g., 'D3::idx2::sandboxing') or display_id (e.g., 'D3.2'). display_id may resolve to multiple subgoals — underlined variants share display_ids.	No	Yes	Not declared	No
`get_reverse_references`Return patterns that reference the given pattern_id in their cross_references. Complement to get_cross_references (outgoing); this shows incoming. Use to find all consumers of a given pattern.	Return patterns that reference the given pattern_id in their cross_references. Complement to get_cross_references (outgoing); this shows incoming. Use to find all consumers of a given pattern.	No	Yes	Not declared	No
`list_operational_heuristics`List operational heuristics distilled from production agentic AI deployment (Claude Code, Rewind). These are cross-cutting safety principles discovered through building and operating AI agents, mapped to framework suites. Optional filters: suite_id (heuristics relevant to a specific suite), query (keyword search across titles and principles). Separate from the normative pattern layer — different category of knowledge.	List operational heuristics distilled from production agentic AI deployment (Claude Code, Rewind). These are cross-cutting safety principles discovered through building and operating AI agents, mapped to framework suites. Optional filters: suite_id (heuristics relevant to a specific suite), query (keyword search across titles and principles). Separate from the normative pattern layer — different category of knowledge.	No	Yes	Not declared	No
`list_requirements`List subgoals matching filters (suite_id, suite_type, content_type, min_confidence, missing_pattern_only). Results capped by limit (default 50, max 100). Every pattern is a model-generated draft (review_status generated_draft; there is no human-review process); confidence is the drafting model's own rating of its draft.	List subgoals matching filters (suite_id, suite_type, content_type, min_confidence, missing_pattern_only). Results capped by limit (default 50, max 100). Every pattern is a model-generated draft (review_status generated_draft; there is no human-review process); confidence is the drafting model's own rating of its draft.	No	Yes	Not declared	No
`list_suites`List all 16 suites in the SaferAgenticAI framework (9 drivers + 7 inhibitors) with subgoal counts and titles. Call this first to orient.	List all 16 suites in the SaferAgenticAI framework (9 drivers + 7 inhibitors) with subgoal counts and titles. Call this first to orient.	No	Yes	Not declared	No
`resolve_id`Resolve a loose reference (partial id, display_id, slug fragment, or title keyword) to canonical pattern_id(s). Case, separator and G/I prefix are normalised (d2.1, D2-1, 'D2 1', G1.2); a hyphen or space returns both the numbered requirement and its underlined variant. Call this when you have a rough reference and need the exact id before calling get_requirement. Always returns candidates — never 'not found'.	Resolve a loose reference (partial id, display_id, slug fragment, or title keyword) to canonical pattern_id(s). Case, separator and G/I prefix are normalised (d2.1, D2-1, 'D2 1', G1.2); a hyphen or space returns both the numbered requirement and its underlined variant. Call this when you have a rough reference and need the exact id before calling get_requirement. Always returns candidates — never 'not found'.	No	Yes	Not declared	No
`search_patterns`Field-weighted keyword search across the framework. Terms match at word starts on lowercased text and are IDF-weighted, so rare terms outrank ubiquitous ones; field weights: title 10x, summary 4x, SFR text 3x (all of a subgoal's SFRs scored as one field), description 2x, pattern body 1x. `matched_in` reports the highest-weighted field that matched. Common practitioner phrases are expanded to the framework's own terms at half weight (reported in `expanded_terms`), and requirement ids such as d2.1, D2-1 or G1.2 are pinned to the top (`matched_in: identifier`). No semantic / embedding search — known limitation, see /mcp.html. Use verbosity='compact' to drop snippets and confidence flags (~70% smaller payload) when triaging.	Field-weighted keyword search across the framework. Terms match at word starts on lowercased text and are IDF-weighted, so rare terms outrank ubiquitous ones; field weights: title 10x, summary 4x, SFR text 3x (all of a subgoal's SFRs scored as one field), description 2x, pattern body 1x. `matched_in` reports the highest-weighted field that matched. Common practitioner phrases are expanded to the framework's own terms at half weight (reported in `expanded_terms`), and requirement ids such as d2.1, D2-1 or G1.2 are pinned to the top (`matched_in: identifier`). No semantic / embedding search — known limitation, see /mcp.html. Use verbosity='compact' to drop snippets and confidence flags (~70% smaller payload) when triaging.	No	Yes	Not declared	No

Details

Registry status: Active
Published: Nov 6, 2026
Updated: Nov 6, 2026
Website: Not given
Repository: https://github.com/NellInc/saferagenticai-mcp⁠ (opens in a new tab)
Categories (suggested): Search and webSuggested categories are assigned automatically from the registry text and may be wrong. Verified operators can correct them.
GDPR: Not declared

Are you the operator? Claim this listing