cursor-mcp-token-facade
Provides a proxied GitHub MCP integration, disabled by default, that authenticates with a GitHub PAT via Authorization header to enable GitHub-related tools behind the facade.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@cursor-mcp-token-facade search tools for filesystem, then read sandbox/hello.txt"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
cursor-mcp-token-facade
MIT · Cursor-facing MCP facade that keeps token spend low by exposing 5 host tools while proxying an unlimited number of child MCP servers behind a staged catalog.
This is the public, generalized package. It ships typical open examples (
filesystem,memory,fetch, …). It does not include private house wiring.
Cursor host (always 5)
search_tools · invoke_tool · mcp_status · search_resources · read_resource
│
▼
staged catalog: mode=names (default) | mode=schema | limit
│
┌────┴────┬──────────┬─────────┐
filesystem memory fetch* github* (* enabled:false until needed)License (why MIT)
License | Fit for this project |
MIT (chosen) | Default for small Node/MCP utilities. Max adoption, trivial for Cursor users to vendor or fork. Matches |
Apache-2.0 | Better if you need an explicit patent grant for corporate legal. Use if your org requires it; functionally similar for this size of tool. |
GPL / AGPL | Poor fit — scares adoption for editor tooling people copy into private configs. |
Recommendation: ship MIT. Keep proprietary child configs (paths, secrets, moat servers) in a private repo; publish only the frozen facade + generic examples.
Related MCP server: MCP-Lens
Why tokens drop (typical model)
Assumptions: ~40 child tools with mid-size JSON schemas; Cursor injects ListTools every turn; agent searches before invoke.
Path | Fat (all schemas on host) | Facade + staged catalog | Δ |
Host ListTools / turn | ~1 000–3 000+ tok | ~100–400 tok (5 slim tools) | often −60% to −90% |
Discover 3 tools | full schemas dumped |
| ~−60% on search |
Idle heavy servers | still listed / sometimes spawned |
| idle tax → 0 |
Exact savings depend on your children. Rule: never put full child schemas on the host; use search_tools → mode=schema only for the tool you are about to call.
Quick start (behind Cursor)
git clone https://github.com/rcjavier/cursor-mcp-token-facade.git
cd cursor-mcp-token-facade
npm install
mkdir -p "${WORKSPACE_ROOT:-$HOME/workspace}/sandbox" # filesystem child root
cp examples/profiles/token-light.child-servers.json child-servers.json
# or: cp child-servers.json.example child-servers.json
chmod +x start.shWire one absolute path into the project .cursor/mcp.json:
{
"mcpServers": {
"cursor-mcp-token-facade": {
"command": "/ABSOLUTE/PATH/cursor-mcp-token-facade/start.sh",
"args": []
}
}
}Disable duplicate marketplace MCP plugins for the same servers you put behind the facade (otherwise Cursor still dumps their tools onto the host).
Reload Cursor MCP.
Agent loop
1. search_tools { "query": "file", "mode": "names", "limit": 10 }
2. search_tools { "query": "filesystem__read_file", "mode": "schema", "limit": 1 }
3. invoke_tool { "tool_name": "filesystem__read_file", "payload": { ... } }Built-ins always available: echo, calc, plus mcp_status.
Child config (typical examples)
Child | Default | How |
| ON |
|
| ON |
|
| OFF | Official demo kitchen-sink server |
| OFF | HTTP fetch MCP |
| OFF | HTTP + |
Flip with "enabled": false and reload. Schema: child-servers.schema.json. Live file child-servers.json is gitignored — never commit secrets.
Env expansion: ${WORKSPACE_ROOT}, ${HOME}, ${GITHUB_PAT}, …
Develop
npm test # staged catalog + token-light profile contracts
npm start # stdio (what Cursor uses)
MCP_FACADE_MODE=http npm run start:daemon # optional localhost JSON door :8766What this is / is not
Is | Is not |
Frozen token-law facade + generic examples | Your private stack / moat MCP wiring |
Drop-in Cursor stdio server | A replacement for Cursor’s plugin OAuth UX |
Safe to open-source under MIT | A dump of machine-specific |
Private, opinionated instances should stay private. Publish the pattern; keep the moat local.
Available Tools
5 toolsinvoke_toolA
Invoke a built-in or child tool by exact name (serverName__toolName). Discover names via search_tools; child roster via mcp_status.
Inputs: payload (required), tool_name (required).
mcp_statusA
Live status of every child MCP server: name, type, enabled, connected, tool/resource counts, tool names, errors. Use this for roster — not search_tools/invoke_tool descriptions.
Inputs: no named parameters.
read_resourceA
Read one MCP resource by URI from the owning child server.
Inputs: uri (required).
search_resourcesB
Search MCP resources across connected children. Call mcp_status for roster.
Inputs: query (required).
search_toolsA
Search child MCP tools by keyword. Default mode=names (name/description/category only). Use mode=schema for one tool (or tight query) to fetch inputSchema. Optional limit caps hits. Call mcp_status for child server roster.
Inputs: query (required), mode, limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool targets a distinct facet of the facade: search_tools (tool discovery), invoke_tool (execution), mcp_status (child server roster), search_resources and read_resource (resource discovery and access). Descriptions actively cross-reference each other to steer agents away from misselection, e.g. 'Use this for roster — not search_tools/invoke_tool descriptions.'
Four of five names follow a clean verb_noun snake_case pattern (search_tools, invoke_tool, search_resources, read_resource). mcp_status breaks the pattern as a noun phrase, though it is still readable and unambiguous.
Five tools is well-suited to a thin facade layer: discovery, invocation, status, and resource read/write-lite operations. Nothing feels redundant or padded, and no core proxy role is left without a tool.
The set covers tool discovery/invocation, server status, and resource search/read, giving a workable lifecycle for proxying child MCP servers. However, MCP prompts (search_prompts/get_prompt) are absent, and there is no bulk schema listing for tools, which could force repeated single-tool fetches.
Related MCP Connectors
Search, vet & assemble MCP servers from your agent: verified tools, risk labels, and trust scores.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
Related MCP Servers
- AlicenseAqualityDmaintenanceProvides per-Subagent MCP controls to any coding agent or client across all your MCPs and prevents context window waste. Loads only 3 tools instead of all your MCP Server's tool definitions. Agents discover tools on-demand, only when needed and only the servers and tools they are allowed.4117 PyPI42MIT
- AlicenseNot gradedqualityDmaintenanceActs as a proxy/router for multiple downstream MCP servers, exposing only meta-tools to the host to reduce token usage, enabling efficient search and invocation of tools from a fleet of servers.8 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables agents to use many MCP servers without context bloat by exposing meta-tools (search, load, call, run_code) that reduce token usage via progressive disclosure and result trimming.MIT
- AlicenseAqualityBmaintenanceEnables agents to search a lightweight catalog, inspect permissions, lazily start trusted MCP servers, and call child tools without keeping all schemas in context. It also loads approved skills on demand and routes third-party additions through a human approval queue.1103 npm1MIT