← Index

Agenda Intelligence

io.github.vassiliylakhonin/agenda-intelligence-md·v1.0.1·Maps & Location
Quality Score
90
/100

Auditable strategic-risk memos for AI agents: sanctions, regulatory, geopolitics, trade.

§00  Trust verdict · v1 advisory ·  method
UNVERIFIEDno verdict on file

Verdict not yet evaluated for this tool. The hybrid eval runs adversarial cases first; coverage rolls out as the corpus expands. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: hybrid eval, four-state verdict, honest limits.

§01  Install
Claude Desktop (uvx)
{
  "mcpServers": {
    "agenda-intelligence-md": {
      "command": "uvx",
      "args": [
        "agenda-intelligence-md"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "<your-anthropic_api_key>",
        "AGENDA_INTELLIGENCE_MODEL": "<agenda_intelligence_model>",
        "AGENDA_INTELLIGENCE_MAX_TOKENS": "<agenda_intelligence_max_tokens>"
      }
    }
  }
}
§02  Environment variables
ANTHROPIC_API_KEY
secret

Optional. When set together with the [llm] extra (pip install 'agenda-intelligence-md[llm]'), the `analyze` tool calls the Anthropic API directly and returns a schema-validated memo. Without this key, `analyze` returns the assembled system_prompt for the host model to complete.

AGENDA_INTELLIGENCE_MODEL

Optional. Anthropic model identifier used when ANTHROPIC_API_KEY is set. Defaults to a current Claude model.

AGENDA_INTELLIGENCE_MAX_TOKENS

Optional. Max tokens for the Anthropic call from `analyze`. Defaults to 4096.

§03  MCP Quality Score  ·  methodology
freshness
25
completeness
15
installability
25
documentation
15
stability
10
§04  Alternatives in Maps & Location