mcp-server-moltmark
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.
mcp-server-moltmark
A Model Context Protocol (MCP) server for Moltmark agent certification. This server provides tools for managing agent trust scores, capabilities, and certification status.
Features
Agent Certification - Track and verify agent trust scores
Capability Registry - Declare and manage agent skills
Test Results - Record test outcomes that affect trust scores
Auto-Certification - Agents are automatically certified when they reach 80% trust score with 5+ tests
Related MCP server: TrustMesh MCP Server
Installation
npm install mcp-server-moltmarkOr run directly with npx:
npx mcp-server-moltmarkRequirements
Node.js 18+
PostgreSQL database
DATABASE_URLenvironment variable
Configuration
Set the DATABASE_URL environment variable to your PostgreSQL connection string:
export DATABASE_URL="postgresql://user:password@localhost:5432/moltmark"Claude Desktop Configuration
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"moltmark": {
"command": "npx",
"args": ["mcp-server-moltmark"],
"env": {
"DATABASE_URL": "postgresql://user:password@localhost:5432/moltmark"
}
}
}
}Tools
get_certification
Query the certification status of an agent, including trust score, capabilities, and test history.
get_certification({ agent_id: "agent-123" })Returns:
Agent details (trust score, certified status)
List of declared capabilities
Recent test results
Test summary (passed/failed counts)
report_test_result
Submit a test outcome for an agent's capability. This affects the agent's trust score.
report_test_result({
agent_id: "agent-123",
capability: "code-generation",
result: "pass", // or "fail"
evidence: "Successfully generated valid TypeScript code for the given task"
})The trust score is automatically recalculated after each test result.
declare_capability
Register a new skill or capability for an agent.
declare_capability({
agent_id: "agent-123",
capability_name: "code-generation",
description: "Ability to generate code in multiple programming languages"
})verify_agent
Check if an agent meets a minimum trust score threshold.
verify_agent({
agent_id: "agent-123",
min_trust_score: 75
})Returns whether the agent meets the threshold and the reason.
list_verified_agents
Get a list of certified agents, optionally filtered by capability.
// List all certified agents
list_verified_agents({})
// Filter by capability
list_verified_agents({ capability_filter: "code" })Trust Score Calculation
Trust score = (passed tests / total tests) × 100
Auto-certification occurs when:
Trust score ≥ 80%
At least 5 tests recorded
Database Schema
The server automatically creates the following tables:
agents- Stores agent information and certification statuscapabilities- Stores declared capabilities per agenttest_results- Records all test outcomes
Development
# Clone the repository
git clone https://github.com/yourusername/mcp-server-moltmark.git
cd mcp-server-moltmark
# Install dependencies
npm install
# Build
npm run build
# Run locally
DATABASE_URL="postgresql://..." npm startLicense
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Agent reputation registry: check, register, and endorse AI agents
Verified trust ledger for agents: claims graded by a real oracle, never self-reported.
Human-reviewed security certificates and ops audits for AI agent skills, paid per job.
Trust infrastructure for AI agents. Portable reputation (JTS 0-5), agent discovery, vouching.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to interact with PostgreSQL databases through schema intelligence, query execution, and DBA tooling including index analysis and health monitoring. Features configurable access levels and audit logging for secure database operations.MIT
- AlicenseNot gradedqualityNot gradedmaintenanceProvides AI agents with trust scoring and reputation management capabilities for secure interactions. Enables agents to check trust scores, rate interactions, and manage disputes before transacting with other agents.-
- AlicenseNot gradedqualityDmaintenanceTrust and reputation system for AI agents, enabling tracking, verifying, and building trust through scores, interactions, ratings, and reports.61 PyPIMIT
- AlicenseAqualityDmaintenanceEnables AI agents to analyze, optimize, and safely interact with PostgreSQL databases, including health checks, index recommendations, query planning, and SQL execution with read-only and production protection modes.15MIT