LangChain is a framework for developing applications powered by language models, providing tools and components to build context-aware, reasoning applications that integrate with external data sources.
Metis gives AI agents expert know-how that named reviewers have approved, and only where its recorded conditions match the situation. High-risk situations go to a person. When an agent sees practice depart from procedure, it can send the expert one short question. Every retrieval is recorded on a hash-linked evidence chain.
6
10
33 PyPI
2
Apache 2.0
Why this server?
Provides a LangChain document loader via the docling-rs[langchain] extra, exposing langchain-docling's DoclingLoader backed by the Rust engine. Documents are converted into structured Markdown/JSON with layout, tables and OCR so they can be fed directly into LangChain pipelines, with a one-import swap from the Python implementation.
It converts documents to Markdown or docling JSON for AI agents. That covers PDFs with layout analysis, table structure and OCR, plus DOCX, PPTX, XLSX, HTML, EPUB, e-mail, images and audio. It serves MarkItDown's "convert_to_markdown" tool under the same name and contract, along with "convert" and "list_input_formats".
18
3
113
MIT
Why this server?
Allows LangChain bots to execute secure cryptocurrency transactions and zero-fee micro-payments via Modexia's crypto infrastructure.
This server allows your AI agents (like Claude, LangChain bots, or custom swarms) to seamlessly execute secure cryptocurrency transactions (USDC) and zero-fee micro-payments straight from their system prompts.
18
2
MIT
Why this server?
Provides a callback handler integration to trace LangChain chains and record LLM calls for observability.
MCP-native LLM observability. Query your Spanlens traces, stats, cost anomalies, and savings from Cursor, Claude Desktop, or any MCP client. Open source (MIT).
7
13
MIT
Why this server?
Provides integration examples for using SignNow eSignature tools within LangChain AI agent frameworks
MCP-native persistent memory for AI agents. Stores and retrieves encrypted memories with Trust Quotient scoring, cross-agent handover protocol, and immutable audit trail. 13 tools. Remote endpoint available.
13
52 PyPI
13
Apache 2.0
Why this server?
Integrates with LangChain agents via MCP adapters, enabling fleet knowledge retrieval, conservation checks, and ternary validation in LangChain workflows.
Enables Claude Code to query and control the SuperInstance fleet, including fleet status, conservation law checks, semantic search, and agent registry.
8
347 npm
MIT
Why this server?
Plugs into LangChain as a retriever and tool set, enabling LangChain agents to query and use the belief store as memory.
Memory for AI agents that keeps every claim with the source it came from, the date it was asserted, and a confidence you can re-weight per source, so your agent can say where a fact came from. Updates supersede or retract instead of overwriting, so you can replay what the store believed on any past date and review contradictions as lint findings.
