Back to Home
az9713 icon

ACI

Verified Safe

by az9713

Overview

A headless MCP server for AI agents (like Claude) to read, write, and reason over a knowledge graph of scientific propositions, enabling storage, semantic search, relationship mapping, intellectual lineage tracing, and contradiction detection.

Installation

Run Command
uv run python src/server.py

Environment Variables

  • OPENAI_API_KEY

Security Notes

The server uses f-strings to construct LanceDB queries (e.g., `id = '{unit_id}'`) within `get_unit` and `delete_unit`. While `unit_id` is expected to be a UUID, there's no explicit input validation to ensure this. A malicious string injected into `unit_id` *could* potentially manipulate the underlying LanceDB predicate if LanceDB's query parser is permissive to non-literal string values, leading to unexpected data access or deletion. However, the risk is mitigated for typical usage within a controlled AI agent environment where inputs are assumed to be well-formed UUIDs. No `eval`, hardcoded secrets, or obvious network vulnerabilities beyond standard OpenAI API calls were found.

Similar Servers

Stats

Interest Score0
Security Score7
Cost ClassMedium
Avg Tokens200
Stars0
Forks0
Last Update2026-01-17

Tags

Scientific researchKnowledge managementAI agent toolsGraph databaseSemantic search