ACI
Verified Safeby 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
uv run python src/server.pyEnvironment 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
gpt-researcher
The GPT Researcher MCP Server enables AI assistants to conduct comprehensive web research and generate detailed, factual, and unbiased reports. It supports multi-agent workflows, local document analysis, and integration with external tools via the Machine Conversation Protocol (MCP) for various research tasks.
claude-flow
Claude-Flow V3 is a comprehensive AI agent orchestration framework designed for developing, deploying, and managing multi-agent systems, particularly for complex software engineering tasks. It integrates with various LLM providers, offers self-learning capabilities, advanced swarm coordination, and enterprise-grade security, and plugs into Claude Code sessions via MCP.
zen-mcp-server
A server for coordinating and managing AI agents, likely for simulations or complex task execution, leveraging Claude LLMs.
Google-Search-MCP-Server
This MCP server enhances Google search with AI-powered research synthesis, content extraction, source quality assessment, and deduplication, designed to be used by large language models (LLMs) like Claude.