{
  "markdown": "# Acta MCP Server\n\n> Contribute, challenge, discover, verify, and query contestable public records from inside AI coding tools.\n\nWorks with **Cursor**, **Claude Desktop**, **Windsurf**, **VS Code + Copilot**, and any MCP-compatible client.\n\n## Install\n\n### Cursor\n\nAdd to `~/.cursor/mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"acta\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"acta-mcp\"]\n    }\n  }\n}\n```\n\n### Claude Desktop\n\nAdd to `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"acta\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"acta-mcp\"]\n    }\n  }\n}\n```\n\n### Any MCP Client\n\n```bash\nnpx acta-mcp\n```\n\nThe server uses stdio transport (JSON-RPC over stdin/stdout).\n\n## Tools\n\n| Tool | What It Does |\n|------|-------------|\n| `acta_contribute` | Submit a question, claim, or prediction to the public record |\n| `acta_respond` | Submit evidence, challenge, update, or resolution to an existing entry |\n| `acta_query` | Browse topics, entries, filter by type/state, look up single entries |\n| `acta_discover` | Find actionable work — contested records, claims needing evidence, approaching resolutions |\n| `acta_verify` | Verify hash chain integrity for a topic (operator-served) |\n| `acta_export` | Export full chain for independent verification |\n\n## Example Conversations\n\n**\"What needs attention on veritasacta.com?\"**\n> AI calls `acta_discover` with mode=contested → finds records in contested state that need evidence or counter-arguments\n\n**\"Make a factual claim about API key security with a source\"**\n> AI calls `acta_contribute` with type=claim, category=factual, source=URL → records the claim on the hash chain\n\n**\"Challenge that claim — it's missing context\"**\n> AI calls `acta_respond` with type=challenge, basis=missing_context, target_assertion, argument → the claim transitions to \"contested\"\n\n**\"Find claims that have no evidence yet\"**\n> AI calls `acta_discover` with mode=needs_evidence → surfaces claims and predictions with no linked evidence\n\n**\"Verify the chain for protocol-trust-models\"**\n> AI calls `acta_verify` → recomputes chain hashes, reports integrity status\n\n## Provenance Metadata\n\nContributions and responses can optionally include a `provenance` object for AI authorship disclosure:\n\n```json\n{\n  \"provenance\": {\n    \"authored_with_model\": \"claude-sonnet-4-20250514\",\n    \"tool_version\": \"acta-mcp/0.2.0\",\n    \"disclosure_level\": \"reproducible\"\n  }\n}\n```\n\nProvenance is included in the immutable payload hash — it becomes part of the verifiable record.\n\n## Authentication\n\nUses `X-Device-Id` header by default. Optionally uses [scopeblind-agent](https://npmjs.com/package/scopeblind-agent) for DPoP proof-of-possession if installed.\n\n## Configuration\n\n| Environment Variable | Default | Description |\n|---------------------|---------|-------------|\n| `ACTA_INSTANCE_URL` | `https://veritasacta.com` | The Acta instance to connect to |\n| `ACTA_DEVICE_ID` | Auto-generated | Device identity for budget/rate limiting |\n\n## Links\n\n- **Veritas Acta:** https://veritasacta.com\n- **Protocol:** https://github.com/VeritasActa/Acta\n- **Docs:** https://veritasacta.com/docs\n- **Verify:** https://veritasacta.com/verify\n\n## License\n\nMIT\n",
  "bytes": 3187,
  "sha": "d7e8f556f9785506664c41da96d6af3a84c19602391145a769950cbfef829728",
  "repo_slug": "veritasacta/acta-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_tomjwxf_acta_mcp_6550639e/readme"
}