Skip to main content
Glama
deenesjakoruzh
phytul

Phloem MCP Server

by phytul
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Phloem

Phloem is an enterprise-grade, self-hosted knowledge base platform built on RAGFlow. It wraps the engine with a typed Node.js API gateway and MCP server for seamless Agent integration.

Phloem (韧皮部) — the vascular tissue that transports nutrients through a plant. Knowledge should flow the same way.

Why Phloem

  • Self-hosted — your documents, your infrastructure, your control. No data leaves your environment.

  • Agent-ready — expose your knowledge base via REST API or MCP server, so AI agents get grounded, retrieval-augmented answers.

  • Typed end-to-end — one OpenAPI contract drives gateway routes, client SDK, and mock layers. Fewer integration surprises.

  • Swappable backend — an adapter layer isolates RAGFlow; swap or upgrade the engine without touching business code.

  • Extensible — a registry of extension points (middleware, routes, MCP tools, web modules) designed for plugin-style customization without forking.

Related MCP server: Modular RAG MCP Server

Architecture

┌────────────┐   REST    ┌─────────────┐            ┌──────────────┐
│  Web UI    │──────────▶│   Gateway   │──adapter──▶│   RAGFlow    │
│  (React)   │           │  (Fastify)  │            │  (submodule) │
└────────────┘           └──────┬──────┘            └──────────────┘
                                │
                         ┌──────┴──────┐
                         │ MCP Server  │  ◀── Claude Desktop, Cursor, custom agents
                         └─────────────┘

Packages

Package

Description

@phloem/shared

Types, Zod schemas, API contracts

@phloem/gateway

Fastify API gateway with adapter layer

@phloem/mcp

MCP server exposing knowledge tools

@phloem/web

React web console (dark, minimal)

@phloem/eslint-config

Shared ESLint flat config

Getting Started

Prerequisites

  • Node.js ≥ 22

  • pnpm ≥ 9

  • Docker (for RAGFlow backend)

Install

git clone --recurse-submodules https://github.com/phytul/phloem.git
cd phloem
pnpm install
cp deploy/docker/.env.example deploy/docker/.env

Run (mock mode — no backend needed)

# Gateway
pnpm --filter @phloem/gateway dev

# Web console (mock data via MSW)
VITE_API_MODE=mock pnpm --filter @phloem/web dev

Run (with RAGFlow)

# Build and start RAGFlow (Lite profile, Infinity engine)
docker compose -f deploy/docker/docker-compose.yml -f deploy/docker/docker-compose.lite.yml up -d

pnpm --filter @phloem/gateway dev
pnpm --filter @phloem/web dev

Verify

curl http://localhost:3000/healthz

API

The REST contract is the single source of truth: openapi.yaml.

Core resources:

  • POST /v1/retrieval — hybrid retrieval across datasets

  • GET/POST /v1/datasets — knowledge base management

  • POST /v1/datasets/{id}/documents — document upload

  • GET /healthz — liveness probe

MCP Tools

Tool

Description

retrieve_knowledge

Hybrid retrieval across knowledge bases

list_datasets

List available knowledge bases

Development

pnpm run build        # build all packages
pnpm run typecheck    # strict TS check across the monorepo
pnpm run lint         # ESLint + Prettier

Commits follow Conventional Commits. Hooks (lint-staged + commitlint) enforce this automatically.

License

Apache-2.0

Links

  • RAGFlow — the underlying engine

  • MCP — Model Context Protocol

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityMaintained
ResponsivenessSyncing

Resources

Related MCP Connectors

Related MCP Servers

  • sage-mcp

    ltaysh0
    F
    license
    Not graded
    quality
    C
    maintenance
    Hybrid semantic search (dense vector + BM25) over local knowledge bases and codebases, exposed as MCP tools for AI agents to search and list knowledge bases.
    -

  • Modular RAG MCP Server

    Nhuajia
    A
    license
    Not graded
    quality
    C
    maintenance
    Exposes RAG-related tools (query_knowledge_hub, list_collections, get_document_summary) via the Model Context Protocol, enabling AI assistants to perform hybrid search, document ingestion, and evaluation on knowledge bases.
    MIT

  • Modular RAG MCP Server

    sjjjlol
    A
    license
    Not graded
    quality
    D
    maintenance
    A pluggable RAG framework that exposes hybrid search, ingestion, and evaluation tools via the Model Context Protocol, enabling AI assistants like Copilot and Claude to query knowledge bases directly.
    MIT