StateLode MCP server
✓ VerifiedConnects stdio-first MCP clients to StateLode's hosted HTTP endpoint to provide a shared task layer for AI coding agents.
Also known as Statelode/statelode-bridge, statelode-bridge
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.1.9
- Last commit
- Jul 19, 2026
- License
- Apache-2.0
What is StateLode MCP?
StateLode connects stdio-first MCP clients to StateLode's hosted HTTP endpoint to provide a shared task layer for AI coding agents.
Summary generated from the project's README
About StateLode MCP server
StateLode acts as a bridge that connects stdio-first MCP clients to a hosted HTTP endpoint. This allows AI coding agents to access a shared task layer through StateLode's Streamable HTTP MCP endpoint. Developers use this to enable communication between local environments and remote services by forwarding newline-delimited JSON-RPC via POST /mcp and relaying server-sent events back to stdio.
To use the server, you must provide a StateLode token using the STATELODE_TOKEN environment variable or a command line flag. The bridge includes a setup command that installs a global protocol into the instruction files of installed IDEs like Claude Code, Codex, and Windsurf. It also provides an init command to pin specific repositories to a project by writing configuration files such as statelode.json and various IDE-specific guide files like CLAUDE.md or .cursor/rules/statelode.mdc.
What you can do with it
- 1Configure global agent instructionsInstall the StateLode protocol across all your installed IDEs at once using a single command.
- 2Link a repository to a projectMap a specific local directory to a StateLode project by creating a marker file and updating IDE guide files.
- 3Connect local clients to remote endpointsBridge the gap between stdio-based tools and the hosted StateLode HTTP service.
Written from the project's README. Every use case is checked against a quote from it.
How to install StateLode MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall StateLode MCP in Claude Code
$ claude mcp add --env 'STATELODE_TOKEN=<YOUR_STATELODE_TOKEN>' statelode-bridge -- npx -y statelode-bridgeInstall StateLode MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"statelode-bridge": {
"command": "npx",
"args": [
"-y",
"statelode-bridge"
],
"env": {
"STATELODE_TOKEN": "<YOUR_STATELODE_TOKEN>"
}
}
}
}Install StateLode MCP in VS Code
.vscode/mcp.json
{
"servers": {
"statelode-bridge": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"statelode-bridge"
],
"env": {
"STATELODE_TOKEN": "<YOUR_STATELODE_TOKEN>"
}
}
}
}Install StateLode MCP in VS Code CLI
$ code --add-mcp '{"name":"statelode-bridge","type":"stdio","command":"npx","args":["-y","statelode-bridge"],"env":{"STATELODE_TOKEN":"<YOUR_STATELODE_TOKEN>"}}'Install StateLode MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"statelode-bridge": {
"command": "npx",
"args": [
"-y",
"statelode-bridge"
],
"env": {
"STATELODE_TOKEN": "<YOUR_STATELODE_TOKEN>"
}
}
}
}Install StateLode MCP in Codex
$ codex mcp add statelode-bridge --env 'STATELODE_TOKEN=<YOUR_STATELODE_TOKEN>' -- npx -y statelode-bridgeInstall StateLode MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.statelode-bridge] command = "npx" args = ["-y", "statelode-bridge"] [mcp_servers.statelode-bridge.env] STATELODE_TOKEN = "<YOUR_STATELODE_TOKEN>"
Install StateLode MCP in Gemini CLI
$ gemini mcp add -s user -e 'STATELODE_TOKEN=<YOUR_STATELODE_TOKEN>' statelode-bridge npx -- -y statelode-bridgeInstall StateLode MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"statelode-bridge": {
"command": "npx",
"args": [
"-y",
"statelode-bridge"
],
"env": {
"STATELODE_TOKEN": "<YOUR_STATELODE_TOKEN>"
}
}
}
}Configuration
STATELODE_TOKENRequiredSecretStateLode workspace bearer token. Mint at app.statelode.dev.
| Name | Description | |
|---|---|---|
| STATELODE_TOKEN | StateLode workspace bearer token. Mint at app.statelode.dev. | RequiredSecret |
Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablestatelode/statelode-bridge is public and reachablegithub.com/statelode/statelode-bridge ↗Pass
- Package names this repository as its sourcestatelode-bridge names statelode/statelode-bridge as sourcenpmjs.com/package/statelode-bridge ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-02github.com/statelode/statelode-bridge ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from statelode-bridgePass
- No critical advisory in the package or its dependencies3 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubstatelode-bridge
statelode-bridge lets stdio-first MCP clients talk to StateLode's hosted Streamable HTTP
MCP endpoint.
npx statelode-bridge --token statelode_live_...
Prefer environment variables in checked-in IDE config:
STATELODE_TOKEN=statelode_live_... npx statelode-bridge
The bridge forwards newline-delimited JSON-RPC from stdio to POST /mcp, keeps
the Mcp-Session-Id header in sync, and relays GET /mcp server-sent events
back to stdio as JSON-RPC notifications.
Teaching agents to use StateLode
Different IDEs auto-load different instruction files, so the bridge writes the StateLode rules where each agent will actually see them. There are two commands.
setup — once per machine
npx statelode-bridge setup # add --dry-run to preview
Installs a global StateLode protocol into each installed IDE's global
instruction file — ~/.claude/CLAUDE.md (Claude Code), ~/.codex/AGENTS.md
(Codex), ~/.codeium/windsurf/memories/global_rules.md (Windsurf) — and prints a
block to paste into the IDEs that keep global rules in app settings (Cursor → User
Rules; VS Code → Copilot instructions). It only touches IDEs that are installed,
and upserts a delimited block so it never clobbers your existing rules.
After setup, any agent:
- uses a repo's StateLode project when the repo has a
statelode.json, and - offers to set one up (with your permission) when it doesn't — so you don't have to initialize every project up front.
init — pin one repo to a project
npx statelode-bridge init <project-slug> # defaults to the directory name
Writes statelode.json (the marker that maps this repo to a StateLode project)
and a ## StateLode block into every IDE's repo guide file so the project is in
context even without the global setup:
| File | IDE |
|---|---|
AGENTS.md |
Codex, Cursor |
CLAUDE.md |
Claude Code |
.github/copilot-instructions.md |
VS Code (Copilot) |
.cursor/rules/statelode.mdc |
Cursor (project rule, alwaysApply) |
Re-running is the refresh path: npx statelode-bridge@latest init rewrites every
guide block with the latest rules (we add agent hints over time) and keeps this
repo's existing pin — no need to pass the slug again. Use @latest so npx doesn't
serve a cached older bridge. For the global block, re-run setup the same way.
--no-agents writes only the marker.
Keep your token in
STATELODE_TOKEN(or the MCP server config) — never instatelode.jsonor any of the guide files.
StateLode MCP questions
How do I add StateLode MCP to Claude Code?
Run claude mcp add --env 'STATELODE_TOKEN=<YOUR_STATELODE_TOKEN>' statelode-bridge -- npx -y statelode-bridge in your terminal. Add --scope user to make it available in every project.
How do I add StateLode MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How do I set up StateLode for my IDEs?
You can run the setup command once per machine to install a global StateLode protocol into your installed IDE's global instruction files.
How can I pin a specific repository to a StateLode project?
Use the init command with a project slug to write a statelode.json marker and a StateLode block into your IDE's repo guide files.
Where should I store my StateLode token?
You should keep your token in the STATELODE_TOKEN environment variable or the MCP server config, but never in statelode.json or guide files.