Click on "Deploy 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., "@mcp-spec-compliance-mcp audit my server's JSON file for spec compliance"
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.
mcp-name: io.github.CSOAI-ORG/mcp-spec-compliance-mcp
MCP Spec Compliance MCP - audits any MCP server
MCP Spec Compliance MCP - audits any MCP server.json against the official spec. HMAC-signed conformity reports. MIT. By MEOK AI Labs.
# Install via pip
pip install mcp_spec_compliance_mcp
# Or install via Smithery
npx -y @smithery/cli@latest install mcp-spec-compliance-mcp --client claudeRelated MCP server: MCPSec
MCP protocol compliant
Easy installation
Well-documented API
Production-ready
Active maintenance
This MCP server is built with EU AI Act compliance built-in:
✅ Article 9 — Risk Management System
✅ Article 13 — Transparency & Instructions for Use
✅ Article 15 — Bias Detection & Testing
✅ Article 26 — FRIA Support (where applicable)
✅ Article 50 — AI Content Watermarking (where applicable)
Need help getting compliant? Book a free 15-min diagnostic →
Need custom development, SLA guarantees, or white-label deployment?
Pro: $99/mo — Full MCP suite + EU AI Act tracking
Enterprise: $499/mo — Custom dev + SLA + Dedicated support
View Pricing → | Contact Sales →
This server is part of the MEOK AI Labs ecosystem — 300+ MCP servers for sovereign AI governance.
Domain | Purpose |
EU AI Act compliance marketplace | |
AI safety & monitoring | |
Sovereign AI platform | |
Legacy modernization |
MIT © CSOAI-ORG
Add to your claude_desktop_config.json (Claude Desktop) or your MCP client config:
{
"mcpServers": {
"mcp-spec-compliance-mcp": {
"command": "uvx",
"args": ["mcp-spec-compliance-mcp"]
}
}
}Or: pip install mcp-spec-compliance-mcp then run the mcp-spec-compliance-mcp command (stdio transport).
Once configured, ask your assistant, for example:
"Use audit_server_json to …"
"Use check_required_fields to …"
"Use check_naming_conventions to …"
Full conformity audit of an MCP server.json.
Args: server_json: The contents of an MCP server.json file. spec_version: Target spec revision. Defaults to latest.
Returns: {pass, score_0_100, errors, warnings, recommendations, spec_version}
Inputs: server_json (required), spec_version.
Lint the slug, version, and tool names.
Args: server_json: server.json contents. tool_names: Optional list of tool names to validate against snake_case convention.
Returns: {pass, issues}
Inputs: server_json (required), tool_names.
Fast gate: only check required fields.
Args: server_json: server.json contents. spec_version: target spec version.
Returns: {pass, missing}
Inputs: server_json (required), spec_version.
Generate a minimal-but-passing server.json template.
Args: org: GitHub org slug. slug: Package slug (must end in -mcp by convention).
Returns: {template}
Inputs: org, slug.
Return the supported MCP spec revisions + which fields are required for each.
Inputs: no named parameters.
HMAC-sign a conformity report so authors can publish it as evidence.
Args: audit_result: Output of audit_server_json().
Returns: {signed, signature, sealed_at, cert_id}
Inputs: audit_result (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 6 tools
audit_server_json substantially overlaps with check_required_fields and check_naming_conventions, since the former is effectively a superset of the two fast gates. However, descriptions clearly frame the latter as lightweight gates, so an agent can reasonably choose between them.
Every tool follows a consistent snake_case verb_noun pattern (audit_server_json, check_required_fields, list_spec_versions, generate_passing_template, sign_conformity_report). No deviations in style or casing.
Six tools is well-scoped for a compliance/linting server, covering audit, fast checks, version lookup, template generation, and signing. Each tool earns its place without redundancy.
The surface covers the full audit-to-evidence lifecycle (check, audit, template, sign) and is largely self-contained. Minor gaps exist, such as no explicit schema-field-level validator or fix/repair operation, but agents can work around these.
Audits any remote agent or MCP URL for JSON-RPC compliance, latency SLA, OpenAPI schema, and HTTP.
Scans remote MCP servers for protocol, security, and TLS issues; exposes scan tools via MCP.
Audit your MCP servers for poisoned tools and leaked secrets, and check AI-generated code for flaws.
Grade MCP servers A to F with the open behavioral litmus. npm: full toolset; hosted: lookups only.
