Safer Agentic AI MCP
About
Read-only MCP server exposing the Safer Agentic AI safety framework: 238 patterns + 14 operational heuristics via 12 query tools; Python stdio.
Details
- Author
- NellInc
- Downloads
- 287
- Categories
- Developer Tools, Other, Security
Jump to
- 12 read‑only tools for safety guidance access
- 238 normative implementation patterns and 14 operational heuristics
- Covers all 16 safety suites (9 Drivers + 7 Inhibitors)
- No authentication or external network calls required
- All framework data is bundled in the package
- stdio transport, Python ≥3.10, MIT licensed
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Safer Agentic AI MCPCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install the package with uvx saferagenticai-mcp or pipx install saferagenticai-mcp, then add a configuration entry to your MCP client. The tools allow you to search patterns, resolve requirements, map a task to relevant safety guidance, and follow cross‑references.
list_suites
List all 16 suites in the SaferAgenticAI framework (9 drivers + 7 inhibitors) with subgoal counts and titles. Call this first to orient.
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.
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).
search_patterns
Field-weighted keyword search across the framework. Substring match on lowercased terms; field weights: title 10x, summary 4x, SFR text 3x, description 2x, pattern body 1x. `matched_in` reports the highest-weighted field that matched. No semantic / embedding search — known limitation, see /mcp.html. Use verbosity='compact' to drop snippets and confidence flags (~70% smaller payload) when triaging.
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.
resolve_id
Resolve a loose reference (partial id, display_id, slug fragment, or title keyword) to canonical pattern_id(s). Call this when you have a rough reference and need the exact id before calling get_requirement. Always returns candidates — never 'not found'.
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.
list_unreviewed
Return patterns that have not been human-reviewed yet (no reviewed_by). Sorted low-confidence first, then needs_human_review flagged, then alpha. Use during Phase 3 review to pick the next pattern to examine.
review_stats
Coverage stats: total patterns, reviewed %, per-suite and per-confidence breakdown. Surfaces load-time validation issue count.
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.
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.
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.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"safer agentic ai mcp": {
"saferagenticai": {
"type": "http",
"url": "https://mcp.saferagenticai.org/mcp"
}
}
}
}McpServers
{
"saferagenticai": {
"type": "http",
"url": "https://mcp.saferagenticai.org/mcp"
}
}Read-only MCP server exposing the Safer Agentic AI safety framework: 238 patterns + 14 operational heuristics via 12 query tools; Python stdio.
Serves the SaferAgenticAI framework (canonical criteria + Implementation Patterns layer) to coding assistants via the Model Context Protocol.
Published to the canonical MCP catalogues — install from a registry-aware client or the CLI below:
- PyPI—saferagenticai-mcp
- Official MCP Registry—io.github.NellInc/saferagenticai-mcp
Also rolling out across the wider MCP ecosystem:mcp.directory,mcpservers.org,PulseMCP(via the registry ingest), andmcp.so.
Option 1 —uvx(fastest, no manual venv)
If you haveuvinstalled, point your MCP client at:
uvx --from git+https://github.com/NellInc/saferagenticai-mcp saferagenticai-mcp
uv handles isolation and caches the install. Works for single-command config lines in~/.claude/mcp.json.
Option 2 —pipx(isolated global install)
pipx install "git+https://github.com/NellInc/saferagenticai-mcp"
Exposessaferagenticai-mcpglobally; updated withpipx upgrade saferagenticai-mcp.
Option 3 — manual venv (works offline from a checkout)
Homebrew / system Python blocks directpip installunder PEP 668, so if you've cloned the repo and want an editable install:
python3 -m venv research/mcp/.venv research/mcp/.venv/bin/pip install -e research/mcp/server
Producesresearch/mcp/.venv/bin/saferagenticai-mcp. Pattern YAML edits in the repo are picked up live (editable mode).
pipx install saferagenticai-mcp # or, with the modern uv toolchain: uv tool install saferagenticai-mcp # or plain pip: pip install --user saferagenticai-mcp
For audit-trail reproducibility, pin the version:pipx install saferagenticai-mcp==0.3.3. The package bundlescriteria-v1.json+ 238 pattern YAMLs + 4 exemplars
- operational_heuristics.yamlinsidesaferagenticai_mcp/_data/, so a wheel install works without any repo checkout. (The 0.3.0 wheel predates the corpus extension and bundles only 214 patterns, no heuristics; 0.3.1 is the first complete build.)
Add to~/.claude/mcp.json(or your IDE's MCP config). Pick the variant that matches your install option.
{ "mcpServers": { "saferagenticai": { "command": "uvx", "args": [ "--from", "git+https://github.com/NellInc/saferagenticai-mcp", "saferagenticai-mcp" ] } } }
{ "mcpServers": { "saferagenticai": { "command": "/absolute/path/to/saferagenticai-mcp" } } }
For a manual venv checkout, the absolute path is<repo>/research/mcp/.venv/bin/saferagenticai-mcp.
Restart Claude Code / your IDE after editing. The server will load on the first tool call from your assistant.
- Canonical framework:assessor/src/data/criteria-v1.json(extracted fromframework.html)
- Pattern layer:research/mcp/suites/<SUITE>/<pattern_id>.yaml(238 files)
- Exemplars:research/mcp/exemplars/.yaml(fallback for four anchor subgoals)
- Operational heuristics:research/mcp/operational_heuristics.yaml(14 heuristics)
At startup the server loads both and builds an in-memory index keyed bypattern_id.display_idlookups are also supported but may resolve to multiple subgoals (underlined variants).
python3 -c " from saferagenticai_mcp.framework_loader import load_framework idx = load_framework() print(f'{len(idx.subgoals)} subgoals, {sum(1 for s in idx.subgoals.values() if s.has_pattern)} with patterns') "
- Canonical framework: followscriteria-v1.json'sversionfield.
- Pattern layer:v1-draftwhile this directory is being populated;v1once reviewed.
- Server: semantic versioning. Current release is0.3.3(full 238-pattern corpus + operational heuristics bundled; argument validation in dispatch; MIT license with bundledLICENSE, corrected package metadata, and MCP-registry ownership token). Pin explicitly for audit reproducibility.
- Hot reload— server stat-walks the source tree on each tool call; edits show up without restart.
- Load-time validation— required fields, content_type enum, confidence enum. Invalid patterns log WARNINGs but don't fail the server.
- find_patterns_for_task— natural-language task → top patterns grouped by suite. Replaces the need for a separate embedding index at current scale.
- Reverse xref index— built at load, queried byget_reverse_references.
- Auth / remote transport (stdio only).
- Embedding-based semantic search — the field-weighted keyword scoring is sufficient at 238 patterns; embeddings would be worth it at 10× this scale.
- mark_reviewedwrite tool — deliberately not added. Phase 3 review edits go through the YAML directly (editor + git diff = auditable); the MCP stays read-only.
This server (the code in this directory) is licensedMIT— seeLICENSE.
The safety-frameworkcontent*it serves (the patterns, canonical criteria, and operational heuristics bundled undersaferagenticai_mcp/_data/) is part of the SaferAgenticAI framework, published underCC-BY-4.0at the repository root. Attribution: Nell Watson and the Agentic AI Safety Community of Practice.
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
Create crafted UI components inspired by the best 21st.dev design engineers.
Bring agent evaluations, observability, and synthetic test set generation directly into your IDE for free with Galileo's new MCP server
An MCP server to help AI assistants to answer questions and generate AccelByte Extend SDK code more effectively .
MCP server for AI Diagram Maker — generate beautiful software engineering diagrams directly inside Cursor, Claude Desktop, Claude Code, or any MCP-compatible AI agent
ALAPI MCP Tools,Call hundreds of API interfaces via MCP
AI-powered SVG animation generator that transforms static files into animated SVG components using the Allyson platform
MCP server that gives AI assistants on-demand access to 1,500+ amCharts docs, ~300 code examples, and 1000+ class API references.
APIMatic MCP Server is used to validate OpenAPI specifications using APIMatic. The server processes OpenAPI files and returns validation summaries by leveraging APIMatic’s API.
One shared context layer for AI agents and humans — live API specs, DB schemas, and versioned contracts across repos so every agent and teammate works from the same source of truth.
Build and deploy full-stack Next.js apps with 98 tools for React, AWS, and MongoDB
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
