MCP Server

What you get

• 214 Implementation Patterns — one concrete pattern per subgoal: 107 code-applicable, 54 governance, 36 process, 17 ecosystem. Each anchored to its SFRs and evidence requirements.
• 10 MCP tools for lookup, filtered listing, field-weighted search, cross-reference navigation, and task-first pattern discovery.
• Task-first lookup — ask “what patterns apply to a tool-using agent executing shell commands?” and the server returns relevant patterns grouped by suite, ranked by field-weighted keyword matching.
• Hot reload — pattern YAML edits are picked up on each tool call, no restart needed.

Install

Pick the path that matches your setup.

1 From PyPI (recommended)

pipx install saferagenticai-mcp
# or
pip install --user saferagenticai-mcp

The wheel bundles criteria-v1.json, 214 pattern YAMLs, and 4 exemplars, so it works without any repo checkout.

2 With uvx (no manual install)

If you have uv installed, your MCP client can launch the server on demand:

uvx saferagenticai-mcp

uv handles isolation and caches the install. This works well as a single-command entry in ~/.claude/mcp.json.

3 Manual venv (editable checkout)

If you have a local checkout and want pattern edits picked up live:

python3 -m venv research/mcp/.venv
research/mcp/.venv/bin/pip install -e research/mcp/server

Produces research/mcp/.venv/bin/saferagenticai-mcp.

Configure (Claude Code)

Add the server to ~/.claude/mcp.json (or your IDE's MCP config). Restart Claude Code after editing; the server loads on the first tool call.

With pipx or PyPI install

"mcpServers": {
  "saferagenticai": {
    "command": "saferagenticai-mcp"
  }
}

With uvx

"mcpServers": {
  "saferagenticai": {
    "command": "uvx",
    "args": ["saferagenticai-mcp"]
  }
}

With a manual venv checkout

Use the absolute path to the venv binary:

"command": "/absolute/path/to/research/mcp/.venv/bin/saferagenticai-mcp"

Tools (10 total)

Tool	Input	Returns
list_suites	—	16 suites with titles and subgoal counts
get_requirement	id, include_pattern	One subgoal plus its Pattern layer; falls back to fuzzy candidates if no exact match
list_requirements	suite / type / content_type / confidence filters	Filtered subgoal list with reliability signals
search_patterns	query, limit	Field-weighted ranked matches with matched_in and snippets
get_cross_references	id, include_inferred	Outgoing adjacencies
get_reverse_references	id	Incoming adjacencies (who cites this pattern)
resolve_id	query	Canonicalise a partial id, slug fragment, or display_id; always returns candidates
find_patterns_for_task	task (natural language)	Top patterns grouped by suite for a task description
list_unreviewed	limit	Patterns without reviewed_by, sorted low-confidence first
review_stats	—	Coverage %, per-suite, per-confidence; plus validation issue count

Data sources

• Canonical framework — extracted from the Safer Agentic AI Recommended Practices and shipped as criteria-v1.json.
• Pattern layer — one YAML file per subgoal under suites/.
• Exemplars — four hand-written anchor patterns used as few-shot references (D3.2 Sandboxing, D7.2 Culture of Safety, D9.2 Compliance, I7.3).

At startup the server loads both layers and builds an in-memory index keyed by pattern_id. display_id lookups (e.g. D3.2) are also supported and may resolve to multiple subgoals when underlined variants exist.

Smoke test

Verify the install without an MCP client:

python3 -c "
from saferagenticai_mcp.framework_loader import load_framework
idx = load_framework()
print(f'{len(idx.subgoals)} subgoals, '
      f'{sum(1 for s in idx.subgoals.values() if s.has_pattern)} with patterns')
"

Two-layer authorship

The framework is served in two layers with different review bars and update cadences:

• Canonical layer — the normative SFRs and evidence requirements, authored by Nell Watson and Ali Hessami. Stable, auditable, versioned via criteria-v1.json.
• Implementation Patterns layer — LLM-drafted, human-reviewed guidance that translates normative requirements into code patterns, governance templates, and process scaffolds. Versioned independently.

Every pattern entry carries provenance: drafted_by, anchor_exemplar, confidence, needs_human_review, and reviewed_by once redlined.

Versioning

• Canonical framework — follows criteria-v1.json's version field.
• Pattern layer — v1-draft during active review; v1 once all patterns have a human reviewed_by.

Scope

• Transport — stdio only; no remote or authenticated transport.
• Search — field-weighted keyword scoring. Sufficient at 214 patterns; embedding-based semantic search would be worth it at ~10× this scale.
• Read-only — no mark_reviewed write tool. Review edits go through the YAML files directly so editor + git diff stay auditable.