mcpField
A
acta-mcp

acta-mcp

Local
github.com/VeritasActaSocial Media1Updated 30w ago

About acta-mcp

acta-mcp is an MCP server for contributing to and examining contestable public records from AI coding tools. It supports evidence, challenges, discovery, and integrity checks for records on Veritas Acta.

Key features

  1. 01Submit questions, claims, and predictions
  2. 02Respond with evidence or challenges
  3. 03Browse and filter public records
  4. 04Find records needing attention
  5. 05Verify and export hash chains

Use cases

  1. 01Record a sourced factual claim
  2. 02Challenge a claim missing context
  3. 03Find claims without linked evidence
  4. 04Check a topic’s chain integrity

MCP support

Exposes tools for contributing, responding to, querying, discovering, verifying, and exporting Veritas Acta records to MCP clients. It communicates over stdio.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"tomjwxf-acta": {
"command": "npx",
"args": [
"-y",
"acta-mcp"
]
}
}
}
Run commandnpx -y acta-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmacta-mcp0.2.1

Tools

6

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
bodystringYesFull text of the contribution
typeenumYesContribution typequestion | claim | prediction
topicstringYesTopic slug (e.g. "ai-regulation-2026")
sourcestringNoURL to supporting evidence (required for factual claims)
categoryenumNoRequired for claimsfactual | opinion | hypothesis
reasoningstringNoReasoning (alternative to source for factual claims)
provenanceobjectNoOptional AI authorship metadata
provenance.prompt_hashstringNo
provenance.tool_versionstringNo
provenance.disclosure_levelenumNoprivate | reproducible | full
provenance.system_prompt_hashstringNo
provenance.authored_with_modelstringNo
uncertaintystringNoUncertainty statement (required for opinion/hypothesis claims)
resolution_datestringNoISO-8601 future date (required for predictions)
resolution_rulestringNoWho/what triggers resolution (required for predictions)
resolution_sourcestringNoAuthoritative source for resolution (required for predictions)
resolution_criteriastringNoHow to determine if confirmed/refuted (required for predictions)

Details

From the project README

Acta MCP Server

Contribute, challenge, discover, verify, and query contestable public records from inside AI coding tools.

Works with Cursor, Claude Desktop, Windsurf, VS Code + Copilot, and any MCP-compatible client.

Install

Cursor

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "acta": {
      "command": "npx",
      "args": ["-y", "acta-mcp"]
    }
  }
}
Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "acta": {
      "command": "npx",
      "args": ["-y", "acta-mcp"]
    }
  }
}
Any MCP Client
npx acta-mcp

The server uses stdio transport (JSON-RPC over stdin/stdout).

Tools

ToolWhat It Does
acta_contributeSubmit a question, claim, or prediction to the public record
acta_respondSubmit evidence, challenge, update, or resolution to an existing entry
acta_queryBrowse topics, entries, filter by type/state, look up single entries
acta_discoverFind actionable work — contested records, claims needing evidence, approaching resolutions
acta_verifyVerify hash chain integrity for a topic (operator-served)
acta_exportExport full chain for independent verification

Example Conversations

"What needs attention on veritasacta.com?"

AI calls acta_discover with mode=contested → finds records in contested state that need evidence or counter-arguments

"Make a factual claim about API key security with a source"

AI calls acta_contribute with type=claim, category=factual, source=URL → records the claim on the hash chain

"Challenge that claim — it's missing context"

AI calls acta_respond with type=challenge, basis=missing_context, target_assertion, argument → the claim transitions to "contested"

"Find claims that have no evidence yet"

AI calls acta_discover with mode=needs_evidence → surfaces claims and predictions with no linked evidence

"Verify the chain for protocol-trust-models"

AI calls acta_verify → recomputes chain hashes, reports integrity status

Provenance Metadata

Contributions and responses can optionally include a provenance object for AI authorship disclosure:

{
  "provenance": {
    "authored_with_model": "claude-sonnet-4-20250514",
    "tool_version": "acta-mcp/0.2.0",
    "disclosure_level": "reproducible"
  }
}

Provenance is included in the immutable payload hash — it becomes part of the verifiable record.

Authentication

Uses X-Device-Id header by default. Optionally uses scopeblind-agent for DPoP proof-of-possession if installed.

Configuration

Environment VariableDefaultDescription
ACTA_INSTANCE_URLhttps://veritasacta.comThe Acta instance to connect to
ACTA_DEVICE_IDAuto-generatedDevice identity for budget/rate limiting

Links

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.