constraints-registry-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@constraints-registry-mcplist constraints for the user-service"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Constraint Registry — V0
A single, queryable source of engineering constraints (infrastructure, organizational, architectural) that coding agents consult at code-generation time, exposed over an MCP server. It does not enforce constraints itself; it delegates validation to existing enforcement engines (e.g. Conftest/OPA).
See constraint-registry-v0-spec.md for the authoritative requirements and
TRACEABILITY.md for requirement→component→test mapping.
Quick start
uv sync
# Run the validation harness (Section 7) against the bundled sample sources:
uv run cregistry-harnessThe harness emits machine-readable JSON and exits non-zero on any failure
(VH-OUTPUT-1), running end-to-end against the self-contained sample sources under
sources/ (VH-OUTPUT-2).
Related MCP server: Domain memory
Running the MCP server
uv run cregistry-mcp # stdio (default; each tool spawns its own)
uv run cregistry-mcp --http --port 8765 # one shared HTTP server for all toolsSee docs/RUNNING.md for per-tool setup (Claude Code / Cursor / Codex),
stop/restart, and macOS launchd auto-start, and docs/MCP_CONTRACT.md for the
tool contracts.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/SureshKhemka/constraints-registry-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server