Constitutional-AI safety guardrails for any LLM — personas, constitutions, adjudication.
Creed Space gives agents machine-readable value systems: pick a persona (ambassador, nanny, sentinel, godparent, muse, anchor), pull its merged constitution, generate complete system prompts, and evaluate actions against declared values. 16 tools, no credentials required — runs against the public Creed Space API.
- Website: https://www.creed.space
- Repo: https://github.com/Creed-Space/creedspace-mcp-server
- npm: `@creedspace/mcp-server` (also installable locally via `npx`)
Cognium trust score
30%
Tier
Unverified
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Last scanned 2026-08-30.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.