AUTOMATIONSWITCH
CommunityAI / ML

Agentset

by agentset-ai (community)

Open-source RAG platform with built-in citations, deep research, 22+ file format support. MCP integration for agent retrieval workflows. 1,983 GitHub stars and 5 commits on main in the last 30 days.

1,983·6 tools·Released SEP 2025·MIT
pip install agentset
Share:

Open-source RAG platform with built-in citations, deep research, 22+ file format support. 1,983 GitHub stars and 5 commits on main in the last 30 days.

Reviewed by M. Nouriel · MAY 2026

INSTALL THIS SERVER

{ "mcpServers": { "agentset": { "command": "python", "args": [ "-m", "agentset" ] } } }
PrereqPyPI: `agentset`. Self-host locally or via Docker; hosted Agentset uses AGENTSET_API_KEY. Path: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS).
{ "mcpServers": { "agentset": { "command": "python", "args": [ "-m", "agentset" ] } } }
{ "mcpServers": { "agentset": { "command": "python", "args": [ "-m", "agentset" ] } } }
{ "mcpServers": { "agentset": { "command": "python", "args": [ "-m", "agentset" ] } } }
{ "mcpServers": { "agentset": { "command": "python", "args": [ "-m", "agentset" ] } } }

6 TOOLS AVAILABLE

ingest_document
Ingest a document (PDF, DOCX, MD, 22+ formats) into the Agentset index
Admin
query
Query the index and return retrieved chunks with citations
Read
list_documents
List documents ingested into the workspace
Read
deep_research
Run a multi-step research task across the index
Read
get_citations
Retrieve citation metadata for a response
Read
delete_document
Remove a document from the index
Admin

OUR ASSESSMENT

Strengths
  • 1,983 GitHub stars.
  • 5 commits on main in the last 30 days.
  • MIT license.
  • 22+ file format ingestion.
  • Built-in citation metadata.
  • Deep-research orchestration included.
Weaknesses
  • Self-hosted setup requires DevOps capacity (vector DB plus orchestration).
  • Query quality depends on chunk-size tuning per corpus.
  • Community-maintained.
Security Notes

AGENTSET_API_KEY (hosted) is account-scoped. Ingested documents may contain PII; restrict the agent flow to a workspace with appropriate retention and access policy.

Best For

RAG-driven agent workflows that need source citations; teams that want one open-source platform across document ingestion, retrieval, and research; cost-conscious orgs avoiding closed RAG vendors.

TECHNICAL DETAILS

Language
python
Transport
stdio
Clients
Claude DesktopClaude CodeCursorVS CodeWindsurf
License
MIT
GitHub
npm
agentset
Last Release
agentset (PyPI latest)MAY 14, 2026
First Released
SEP 1, 2025

ADOPTION METRICS

// GitHub Stars
1,983

// Reading this1,983 stars on agentset-ai/agentset. 5 commits on main in the last 30 days.

// Popularity Rank
#13
Globally · #13 in AI / ML

// Reading thisPairs with Pinecone, Qdrant, Cognee, Codebase Memory, Arize Phoenix, MLflow, W&B, Engram, Mastra in ai-ml. Agentset owns the open-source RAG-with-citations slot.

SOURCES & VERIFICATION

We don't take any single directory's word for it. Before scoring, we cross-reference 4 public MCP sources, install the server ourselves against the clients we cover, and record when we last re-verified.

01
Discovered
Manual submission
First indexed MAY 14, 2026
02
Cross-referenced
4 directories
PulseMCP, MCP.so, Glama, Smithery
03
Verified against
Claude Desktop, Cursor
Installed and tested across clients
04
Last re-checked
MAY 14, 2026
Weekly re-verification
// How other directories see it

The same server, 4 different lenses. We reconcile these signals into our editorial score, which is why our number sometimes diverges from a directory-aggregate star count.

SourceTheir ratingTheir star countTheir downloadsLast synced
AutomationSwitch This page4.3editorial1,983MAY 14, 2026
PulseMCP— unratedunavailableunavailableMAY 14, 2026
MCP.so— unratedunavailableunavailableMAY 14, 2026
Glama— unratedunavailableunavailableMAY 14, 2026
Smithery— unratedunavailableunavailableMAY 14, 2026

// Counts are directory-reported; we don't adjust them. Discrepancies usually come from different snapshot times or star-caching.

OTHER AI / ML MCP SERVERS

Community4.6

Cognee MCP

topoteretes

Knowledge graph plus vector memory engine for AI agents, exposed as an MCP server with V2 session-aware memory tools (remember, recall, forget, improve) and classic V1 ingestion pipelines (cognify, codify). Three transports: stdio, SSE, Streamable HTTP. 16,965 GitHub stars, Apache-2.0.

8 tools16,997
Official4.6

HeyGen Hyperframes

HeyGen

Write HTML, render video. Built for agents. HeyGen's framework that turns HTML templates into video output via MCP. 16,400 GitHub stars and 100 commits on main in the last 30 days.

6 tools16,400
Community4.6

Codebase Memory MCP

DeusData

High-performance code intelligence MCP server for AI coding agents. Indexes a codebase into a queryable knowledge graph in milliseconds, with 14 MCP tools spanning structural search, call-chain tracing, impact analysis, dead-code detection, and Cypher queries. Single static C binary, 66 languages via tree-sitter, zero runtime dependencies.

9 tools2,021
Vendor4.5

Arize Phoenix MCP

Arize AI

LLM observability platform exposing prompts, projects, traces, spans, sessions, datasets, and experiments through MCP. Published to npm as @arizeai/phoenix-mcp, current 4.0.8 (2026-04-29). 9,496 stars on parent monorepo, Elastic License 2.0.

8 tools9,496
Vendor4.5

Qdrant MCP Server

Qdrant

Official Qdrant vector database MCP server. Acts as a semantic memory layer on top of Qdrant: store information with metadata, retrieve via similarity search. Two tools, very small surface area, exceptionally maintained by the Qdrant team. Configurable embedding provider (fastembed default), supports remote and local Qdrant clusters.

2 tools1,373
Community4.4

Mastra

mastra-ai (Gatsby team)

TypeScript framework for building AI-powered applications and agents, with built-in MCP server support. From the team behind Gatsby. 23,680 GitHub stars and 100 commits on main in the last 30 days.

6 tools23,680
// Get in touch

DISCUSS YOUR
MCP REQUIREMENTS.

Evaluating a server, scoping an internal deployment, or working out whether MCP is the right fit at all. Start the conversation and we will point you at the right piece of the ecosystem.

Discuss Your MCP Requirements →