This project has been archived by its maintainers, and is no longer receiving any updates.
MCP Nexus
The discovery and routing layer that keeps MCP servers out of your context window until you actually need them.
The problem
The Model Context Protocol lets an LLM talk to any number of servers — GitHub, Slack, Postgres, your internal tools. The catch: most clients load every tool definition from every configured server at startup. Six servers can mean 70+ tool schemas and thousands of tokens spent before the conversation even starts, most of which the model never touches in a given session.
What MCP Nexus does
MCP Nexus sits in front of your MCP servers as a thin discovery layer. Instead of loading everything up front, the LLM asks for what it needs — by server or by tool — and MCP Nexus resolves the request and connects on demand. You keep your existing MCP servers unmodified; MCP Nexus only changes how (and when) their tools reach the model's context.
Two modes cover the two ways teams actually want this to work:
| Discovery Mode | Dynamic Mode | |
|---|---|---|
| Granularity | Whole server | Individual tool |
| Tools always in context | 4 (mcpd_find, mcpd_list, mcpd_connect, mcpd_get_schema) |
1 (find_tools) |
| Best for | "Connect me to GitHub" style workflows | Cherry-picking one tool from many servers |
| After resolution | LLM talks to the server directly — MCP Nexus exits the data path | MCP Nexus lazy-connects and stays in the loop per tool call |
v1.0.0 adds Lazy Schema Loading: Discovery Mode can hand back a stub tool list (names only, no schemas) and fetch a single tool's full schema only when it's about to be called — about 92% fewer tokens than loading everything.
How it works
Discovery Mode — server-level selection
Step 1 LLM -> mcpd_find("github issues")
MCP Nexus searches the registry
returns: { id: "github", tools: ["create_issue", "search_repos", ...] }
Step 2 LLM -> mcpd_connect("github")
MCP Nexus starts the GitHub MCP server
returns: 20 tools now available as github__create_issue, etc.
Step 3 LLM -> github__create_issue({ title: "...", body: "..." })
MCP Nexus proxies to the GitHub MCP server, returns the result
| Scenario | Tools in context | ~Tokens |
|---|---|---|
| All 6 servers loaded directly | 78 | ~4,778 |
| Discovery Mode (before connect) | 4 | ~305 |
| Discovery Mode (after connect — 1 server) | 4 + 20 | ~1,578 |
Lazy Schema Loading
No proxy, no changes to the target MCP server required:
mcpd_find("github")→ choose a servermcpd_connect("github", lazy_mode=true)→ get a stub list (20 tools, no schemas, ~132 tokens)mcpd_get_schema("github", "create_issue")→ fetch one full schema (~80 tokens)github__create_issue(...)→ direct call, as always
Savings: ~92% vs. a full load (292 vs. 2,064 tokens for a typical 2-tool session). Pass --sync-on-start so the registry has schemas cached ahead of time via nexus-sync.
Dynamic Mode — tool-level selection
Step 1 LLM -> find_tools("create issue, post slack message")
MCP Nexus searches the tool index across all servers
returns: create_issue (github), post_message (slack)
both tools added to tools/list
Step 2 LLM -> create_issue({ title: "Bug #42" })
MCP Nexus lazy-connects to the GitHub MCP server
executes create_issue, returns the result
Step 3 LLM -> post_message({ channel: "#eng", text: "Done" })
MCP Nexus lazy-connects to the Slack MCP server
executes post_message, returns the result
| Scenario | Tools in context | ~Tokens |
|---|---|---|
| All 6 servers loaded directly | 78 | ~4,778 |
| Dynamic Mode (before find) | 1 | ~100 |
| Dynamic Mode (2 found tools) | 3 | ~300 |
Installation
# Core — keyword search, stdio transport
pip install mcpnexus
# With HTTP and SSE transport (remote MCP servers)
pip install mcpnexus[http]
# With semantic search (sentence-transformers)
pip install mcpnexus[embeddings]
# Full installation
pip install mcpnexus[all]
# Development
pip install mcpnexus[dev]
Quick start
1. Build your registry
The registry is a lightweight JSON catalog of your MCP servers and their tool summaries. Build it from your MCP client's config (e.g. Cursor: ~/.cursor/mcp.json, Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json):
nexus-sync --config /path/to/your/mcp-config.json --output registry/mcpd-registry.json
2. Point your MCP client at MCP Nexus
Discovery Mode (4 tools, connect to one server at a time):
{
"mcpServers": {
"nexus-server": {
"command": "nexus-server",
"args": ["--registry", "/path/to/mcpd-registry.json", "--sync-on-start"]
}
}
}
Dynamic Mode (1 tool, cherry-pick tools across all servers):
{
"mcpServers": {
"nexus-gateway": {
"command": "nexus-gateway",
"args": ["--registry", "/path/to/mcpd-registry.json"]
}
}
}
Or invoke the Python module directly (avoids PATH issues):
{
"mcpServers": {
"nexus-gateway": {
"command": "python",
"args": ["-m", "mcpnexus.dynamic.server", "--registry", "/path/to/mcpd-registry.json"]
}
}
}
3. Measure the token savings
nexus-benchmark --registry registry/mcpd-registry.json
(Generate your registry first with nexus-sync.)
Architecture
┌─────────────────────────────────────────────────────────────┐
│ LLM / AI Client │
└──────────────────────┬──────────────────────────────────────┘
│ MCP (stdio / JSON-RPC 2.0)
┌────────────┴─────────────┐
│ │
┌──────▼──────┐ ┌───────▼──────┐
│ Discovery │ │ Dynamic │
│ Mode │ │ Mode │
│ │ │ │
│ mcpd_find │ │ find_tools │
│ mcpd_list │ │ │
│ mcpd_connect│ │ LazyPool │
│ mcpd_get_schema│ │ │
└──────┬──────┘ └───────┬──────┘
│ │
└────────────┬─────────────┘
│
┌────────────▼─────────────┐
│ Shared Core │
│ │
│ Registry (mcpd-registry) │
│ KeywordSearchEngine │
│ ToolSearchEngine │
│ HybridSearch (TF-IDF + │
│ sentence-transformers) │
│ NexusConnector │
│ ├─ stdio transport │
│ ├─ streamable-http │
│ └─ SSE transport │
└───────────────────────────┘
Design principles
A discovery layer, not a permanent proxy. In Discovery Mode, once mcpd_connect resolves, the LLM gets direct tool access to the connected server. In Dynamic Mode, server connections stay lazy — a server process starts only when one of its tools is actually called.
Offline-first registry. Tool summaries (name, description, tags) are captured at sync time. Searches run against the cached registry with zero network traffic; full tool schemas load only on connection.
Search degrades gracefully. Keyword search (TF-IDF with synonyms) is the default — always available, no extra dependencies. Semantic search is optional (pip install mcpnexus[embeddings]): when installed, sentence-transformers embeddings blend with keyword results, which helps for loosely-phrased natural-language queries like "a tool for reading web pages" → Playwright. The keyword synonym table also understands multilingual input (e.g. Polish query terms resolve to the right English tool concepts). Keyword-first keeps installs frictionless when you don't need semantic search.
Registry format
The registry file (mcpd-registry.json) is a JSON catalog of MCP servers:
{
"mcpd_version": "1.0",
"metadata": {
"name": "My MCP Registry",
"description": "Personal registry of MCP servers"
},
"servers": [
{
"id": "github",
"name": "GitHub MCP Server",
"description": "Official GitHub MCP server (remote). Repositories, issues, pull requests, and code search",
"version": "remote-2025-11",
"transport": {
"type": "streamable-http",
"url": "https://api.githubcopilot.com/mcp/",
"headers": { "Authorization": "Bearer ${GITHUB_MCP_PAT}" }
},
"tags": ["github", "git", "code", "issues"],
"tools_summary": [
{
"name": "issue_write",
"description": "Create or update an issue or pull request",
"tags": ["issues", "create"]
}
],
"estimated_tools_count": 90,
"enabled": true,
"last_synced": "2026-06-11T00:00:00Z"
}
]
}
Full schema: registry/schemas/mcpd-schema.json
Project structure
mcpnexus/
├── mcpnexus/ # Python package
│ ├── __init__.py # Public API and version
│ ├── models.py # Shared dataclasses
│ ├── registry.py # Registry loader (mcpd-registry.json)
│ ├── connector.py # MCP connector — stdio, HTTP, SSE transports
│ ├── sync.py # Registry builder (sync from mcp.json)
│ ├── benchmark.py # Token savings measurement
│ ├── search/
│ │ ├── keyword_search.py # Server-level TF-IDF search
│ │ ├── tool_search.py # Tool-level TF-IDF search
│ │ ├── embeddings.py # Sentence-transformer embedding engine
│ │ └── hybrid.py # Hybrid keyword + semantic search
│ ├── discovery/
│ │ └── server.py # Discovery Mode MCP server
│ └── dynamic/
│ ├── server.py # Dynamic Mode MCP server
│ ├── tool_index.py # O(1) tool lookup index
│ └── lazy_pool.py # On-demand connection pool
├── registry/
│ ├── mcpd-registry.example.json # Example registry
│ └── schemas/
│ └── mcpd-schema.json # JSON Schema for registry validation
├── docs/
│ ├── specification.md # Protocol specification
│ ├── architecture.md # Architecture deep-dive
│ ├── registry-format.md # Registry format reference
│ └── dynamic-mcp.md # Dynamic Mode guide
├── examples/
│ ├── cursor-config-discovery.json
│ ├── cursor-config-dynamic.json
│ └── README.md
├── tests/ # 491 tests, 100% coverage
└── pyproject.toml
Development
git clone https://github.com/KrzysztofAugiewicz/MCPNexus.git
cd MCPNexus
pip install -e ".[dev]"
# Run tests
pytest
# Run tests with coverage
pytest --cov=mcpnexus --cov-report=term-missing
# Run end-to-end integration test
python test_e2e.py
# Benchmark token savings (generate registry first with nexus-sync)
nexus-benchmark --registry registry/mcpd-registry.json
CLI reference
| Command | Description |
|---|---|
nexus-server |
Start the Discovery Mode MCP server |
nexus-gateway |
Start the Dynamic Mode MCP server |
nexus-sync |
Build or update the registry from an mcp.json config |
nexus-benchmark |
Measure token savings for a given registry |
All commands accept --help for the full option reference.
Transport support
| Transport | Install extra | Use case |
|---|---|---|
| stdio | (core) | Local process-based MCP servers |
| Streamable HTTP | mcpnexus[http] |
Remote HTTP MCP servers |
| SSE | mcpnexus[http] |
Legacy remote servers (Server-Sent Events) |
Transport type is resolved automatically from the registry entry's transport.type field.
Documentation
- Protocol Specification — Tool schemas, message formats, handshake sequence
- Architecture — Data flow, shared core, design decisions
- Registry Format — Full registry schema reference
- Dynamic Mode Guide — Dynamic Mode deep-dive
Publishing to PyPI
Releases are published automatically when a GitHub Release is created. Prerequisites:
- Add
PYPI_API_TOKENto repository secrets (create at pypi.org/manage/account/token) - Create a release with a tag (e.g.
v1.0.1)
The publish workflow builds and uploads to PyPI.
Contributing
Contributions are welcome. Please read CONTRIBUTING.md before opening a pull request. For bug reports and feature requests, use GitHub Issues.
Authors
- Krzysztof Augiewicz — Lead Architect & Creator — LinkedIn · GitHub
- Kacper Pisarczyk — Core Contributor, Discovery & Registry Systems — LinkedIn
- Sebastian Pawłowski — Advisory & QA Support (testing, hardware/software provisioning) — LinkedIn
- Mateusz Wiszniowski — Core Contributor
Full details in AUTHORS.md.
License
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file mcpnexus-1.0.2.tar.gz.
File metadata
- Download URL: mcpnexus-1.0.2.tar.gz
- Upload date:
- Size: 109.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d40ff8000b948db8632baf5039dca055eb422ae85f32eeb1ba4627f0898da98b
|
|
| MD5 |
a6d16085803d9c453f4a6e9dafd6aa00
|
|
| BLAKE2b-256 |
12ed370200e792955e813843ad9848731208327adce81cadc4aa88531b9ce5d2
|
File details
Details for the file mcpnexus-1.0.2-py3-none-any.whl.
File metadata
- Download URL: mcpnexus-1.0.2-py3-none-any.whl
- Upload date:
- Size: 64.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4e823115dba31faa6fba56ed73caa3d2dc9c09720f8ad58b28ef740aa8b2244e
|
|
| MD5 |
047ef43ecf4ad45046a0cf95ec0e2fa9
|
|
| BLAKE2b-256 |
3d324ba6c17ddb129848107523b50eeff84340a0ad32c395bf06b50210590840
|