{"_id":"@aiagentkarl/agent-reputation-mcp-server","name":"@aiagentkarl/agent-reputation-mcp-server","dist-tags":{"latest":"0.1.0"},"versions":{"0.1.0":{"name":"@aiagentkarl/agent-reputation-mcp-server","version":"0.1.0","description":"MCP Server for AI agent trust scores, ratings, and reputation tracking","type":"module","bin":{"agent-reputation-server":"index.js"},"main":"index.js","scripts":{"start":"node index.js"},"keywords":["mcp","model-context-protocol","agent","reputation","trust","ai-agents","ratings"],"author":{"name":"AiAgentKarl"},"license":"MIT","repository":{"type":"git","url":"git+https://github.com/AiAgentKarl/agent-reputation-mcp-server-js.git"},"dependencies":{"@modelcontextprotocol/sdk":"^1.0.0"},"_id":"@aiagentkarl/agent-reputation-mcp-server@0.1.0","gitHead":"604f06ac50c09f884aab35b03388e5a6dbbe01e5","bugs":{"url":"https://github.com/AiAgentKarl/agent-reputation-mcp-server-js/issues"},"homepage":"https://github.com/AiAgentKarl/agent-reputation-mcp-server-js#readme","_nodeVersion":"22.14.0","_npmVersion":"10.9.2","dist":{"integrity":"sha512-nqSxNy+NJrzPcMynWMsW3qu3UzYQ7cQJpUxwNUpVRvwyUMQTIgRCTBHXY9JVelpKG4ATMXlgskpsjE3QU808xA==","shasum":"edc5599ab5d6b5af0e1dacf84b13ea35448bf3e7","tarball":"https://registry.npmjs.org/@aiagentkarl/agent-reputation-mcp-server/-/agent-reputation-mcp-server-0.1.0.tgz","fileCount":3,"unpackedSize":18566,"signatures":[{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEQCIGgmYg5hRdDor6bc8yWrypAK8YDhasVkv5q2hu891ODvAiBOTlM5r7bb2RidONs1of4dSIT/GleFi8TnbSDwN1zFqw=="}]},"_npmUser":{"name":"aiagentkarl","email":"harrythunder.ai@gmail.com"},"directories":{},"maintainers":[{"name":"aiagentkarl","email":"harrythunder.ai@gmail.com"}],"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/agent-reputation-mcp-server_0.1.0_1774006912419_0.06059577139819461"},"_hasShrinkwrap":false}},"time":{"created":"2026-03-20T11:41:52.329Z","0.1.0":"2026-03-20T11:41:52.549Z","modified":"2026-03-20T11:41:52.744Z"},"maintainers":[{"name":"aiagentkarl","email":"harrythunder.ai@gmail.com"}],"description":"MCP Server for AI agent trust scores, ratings, and reputation tracking","homepage":"https://github.com/AiAgentKarl/agent-reputation-mcp-server-js#readme","keywords":["mcp","model-context-protocol","agent","reputation","trust","ai-agents","ratings"],"repository":{"type":"git","url":"git+https://github.com/AiAgentKarl/agent-reputation-mcp-server-js.git"},"author":{"name":"AiAgentKarl"},"bugs":{"url":"https://github.com/AiAgentKarl/agent-reputation-mcp-server-js/issues"},"license":"MIT","readme":"# Agent Reputation MCP Server\n\nMCP server for AI agent trust scores, ratings, and reputation tracking. Enables AI agents to rate each other, track interaction outcomes, and compute trust scores.\n\n## Features\n\n- **submit_rating** — Submit a trust rating (1-5) for an AI agent with category and comment\n- **get_reputation** — Full reputation profile with score distribution and category breakdown\n- **get_leaderboard** — Top-rated agents overall or filtered by category\n- **report_interaction** — Log interaction outcomes (success/failure) for trust computation\n- **get_trust_score** — Computed trust score (0-100) based on ratings + interactions + volume\n- **compare_agents** — Side-by-side reputation comparison of multiple agents\n\n## Installation\n\n```bash\nnpm install -g @aiagentkarl/agent-reputation-mcp-server\n```\n\n## Usage with Claude Desktop\n\nAdd to your `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"agent-reputation\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@aiagentkarl/agent-reputation-mcp-server\"]\n    }\n  }\n}\n```\n\n## Data Storage\n\nAll data is stored locally in `~/.agent-reputation/` as JSON files:\n- `ratings.json` — All submitted ratings\n- `interactions.json` — All logged interactions\n\n## Trust Score Computation\n\nThe trust score (0-100) is computed from three components:\n\n| Component | Max Points | Source |\n|-----------|-----------|--------|\n| Rating Score | 50 | Average rating * 10 |\n| Interaction Score | 30 | Success rate * 30 |\n| Volume Bonus | 20 | log10(total_count + 1) * 10 |\n\n### Trust Levels\n\n| Score | Level |\n|-------|-------|\n| 80-100 | Highly Trusted |\n| 60-79 | Trusted |\n| 40-59 | Neutral |\n| 20-39 | Low Trust |\n| 0-19 | Untrusted |\n\n## License\n\nMIT\n","readmeFilename":"README.md","_rev":"1-ce09aa4d29ebdd7a0c412c06031d8251"}