public-mcp
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
public-mcp
A public MCP server on AWS Lambda that exposes deterministic checking tools.
Status: Plan 01 implemented: the three spec.* tools run locally over stateless
Streamable HTTP. No AWS deployment yet (Plan 03).
Principle: no server-side LLM: the client brings the model, the server checks, validates, seals.
See Roadmap.md and .claude/plans/Plan-01.md.
Tools
Tool | Input | Result |
|
|
|
|
|
|
|
|
|
All inputs are text; caller code is parsed, never executed. Each text field may be at most
32 KiB (UTF-8) and an HTTP body at most 80 KiB. Invalid input (too large, not valid Python,
too deeply nested) is an MCP tool error (isError: true) whose message names the field.
Related MCP server: ai-guardrail-mcp
Run locally
Requires Python 3.12 or newer.
python -m venv .venv.venv/bin/pip install -e ".[dev]".venv/bin/pytest.venv/bin/ruff check .Start the server (endpoint http://127.0.0.1:8000/mcp; --host/--port or
PUBLIC_MCP_HOST/PUBLIC_MCP_PORT override the defaults):
.venv/bin/python -m public_mcp.httpInspect it with the MCP Inspector (UI), or list the tools from the command line:
npx @modelcontextprotocol/inspector@0.17.2 --cli http://127.0.0.1:8000/mcp --transport http --method tools/listAdd it to Claude Code:
claude mcp add --transport http public-mcp http://127.0.0.1:8000/mcpLayout
src/public_mcp/
server.py build_server(): registers the tools, transport-agnostic
http.py local stateless Streamable HTTP entry (python -m public_mcp.http)
limits.py MAX_FIELD_BYTES, MAX_BODY_BYTES, check_field()
errors.py tool error messages
spec/ the checking core: pure, standard library only
tools/ one adapter per tool: limits -> core -> structured result
tests/Provenance and licence
src/public_mcp/spec/ is derived from Agora v0.1.0
(Copyright 2026 Agora contributors, Apache License 2.0) and maintained here; each module's
docstring names its source file, the functions taken and the changes made. This project is
licensed under the Apache License 2.0 (see LICENSE).
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP Spec Compliance MCP — audits any MCP server.json against the official Model Context Protocol
Statically audits MCP tool surfaces for token cost, schema quality, and design issues.
Manage SysML2 projects; check, evaluate, verify, query, document and diagram models.
Evidence-readiness MCP server: validate, audit, and score briefs, memos, and evidence packs.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables users to validate MCP servers, skills, extensions, and packages for schema, security, functional, and semantic quality directly from their MCP client.MIT
- AlicenseBqualityCmaintenanceEnables input/output policy validation via MCP, including scanning text for policy and safety issues, generating test suite outlines, and checking configuration health.35 npmISC
- AlicenseNot gradedqualityCmaintenanceEnables coding agents to select bounded Python source context, run configured checks, and retrieve compact failure reports, diagnostic comparisons, and freshness evidence tied to the checked code.MIT
- AlicenseNot gradedqualityAmaintenanceEnables MCP clients to evaluate text or local files for LLM-output quality issues, returning 0-100 scores, grades, and precise line/column findings. It also lets clients list all available lint rules and severities.MIT