Gcontext

by bleak-ai

8 stars

265 downloads

Not rated

GitHub Website

About

Let your agent operate your infra without seeing your secrets. Structure syncs to cloud, secret values never leave your machine.

Details

Author: bleak-ai
GitHub stars: 8
Downloads: 265
Categories: Developer Tools, Infrastructure, Productivity

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below
Plugin Name Gcontext

Command (node, npx, python, etc.) uvx
Arguments
- Argument 1 gcontext-mcp
Environment
- GCONTEXT_TOKEN <your token>
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "gcontext": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "gcontext-mcp"
            ],
            "env": {
                "GCONTEXT_TOKEN": "<your token>"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "gcontext": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "gcontext-mcp"
            ],
            "env": {
                "GCONTEXT_TOKEN": "<your token>"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "gcontext": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "gcontext-mcp"
            ],
            "env": {
                "GCONTEXT_TOKEN": "<your token>"
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "gcontext": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "gcontext-mcp"
            ],
            "env": {
                "GCONTEXT_TOKEN": "<your token>"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "gcontext": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "gcontext-mcp"
            ],
            "env": {
                "GCONTEXT_TOKEN": "<your token>"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "gcontext": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "gcontext-mcp"
            ],
            "env": {
                "GCONTEXT_TOKEN": "<your token>"
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "gcontext": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "gcontext-mcp"
            ],
            "env": {
                "GCONTEXT_TOKEN": "<your token>"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "gcontext": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "gcontext-mcp"
            ],
            "env": {
                "GCONTEXT_TOKEN": "<your token>"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "gcontext": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "gcontext-mcp"
            ],
            "env": {
                "GCONTEXT_TOKEN": "<your token>"
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "gcontext": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "gcontext-mcp"
            ],
            "env": {
                "GCONTEXT_TOKEN": "<your token>"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "gcontext": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "gcontext-mcp"
            ],
            "env": {
                "GCONTEXT_TOKEN": "<your token>"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "gcontext": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "gcontext-mcp"
            ],
            "env": {
                "GCONTEXT_TOKEN": "<your token>"
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "gcontext": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "gcontext-mcp"
            ],
            "env": {
                "GCONTEXT_TOKEN": "<your token>"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "gcontext": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "gcontext-mcp"
            ],
            "env": {
                "GCONTEXT_TOKEN": "<your token>"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "gcontext": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "gcontext-mcp"
            ],
            "env": {
                "GCONTEXT_TOKEN": "<your token>"
            }
        }
    }
}

From the repository

Follow the repository README to install the server and add its MCP configuration to your client.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "gcontext": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "gcontext-mcp"
            ],
            "env": {
                "GCONTEXT_TOKEN": "<your token>"
            }
        }
    }
}

Type

"stdio"

Command

"uvx"

Args

[
    "gcontext-mcp"
]

Env

{
    "GCONTEXT_TOKEN": "<your token>"
}

A framework for building stateful agents. An agent is a folder of plain files (instructions, connections, secrets, knowledge modules, scripts) served over MCP by a local HTTP server. Runtimes (Claude Code, Desktop, Codex, Cursor) connect to the URL and do the reasoning; gcontext keeps the state.

- Features
- Install
- Quickstart
- The folder
- Your first connection
- CLI
- Agents
- Going further
- Scope
- License

- State that survives sessions- the folder persists across runtimes and clients; nothing is lost between conversations
- Any MCP client- Claude Code, Claude Desktop, Codex, Cursor, or anything that speaks MCP
- Connections- declare service integrations with secret names and Python deps; values stay on your machine, injected at runtime, scrubbed from output
- Modules- accumulated knowledge on a topic, one folder per domain, growing over time
- Scripts-run_scriptfor saved procedures,run_adhoc_scriptfor one-off code, both with secret injection and output scrubbing
- Commands- markdown or Python files that register as slash commands in your client
- Dashboard- read-only web UI with file browser, connection status, and live activity feed
- Context ledger-gcontext contextlists every channel through which context reaches the agent, so you always know what it sees
- Installable agents-gcontext add <id>installs a pre-built agent from the registry

gcontext needs uv: it installs the tool and manages each agent's script environment at runtime. No uv yet? One line, no prerequisites (it brings its own Python if needed):

curl -LsSf https://astral.sh/uv/install.sh | sh # or: brew install uv

gcontext init my-agent # create the state folder gcontext up my-agent # serve it at http://127.0.0.1:4242/mcp

Then connect a client (once, from any directory):

claude mcp add --transport http my-agent http://127.0.0.1:4242/mcp

gcontext connect claude|desktop|codex|cursorprints the exact steps per client. The server logs each client as it connects. Stopping the server (Ctrl+C) disconnects everything; there is no other cleanup.

my-agent/ gcontext.yaml # name, description, optional port agent.md # your agent's definition, pushed to every client at connect secrets.env # secret values, gitignored connections/ # services the agent can use stripe/ connection.yaml # secret names + Python deps index.md # API notes, usage patterns modules/ # accumulated knowledge archive/ # excluded from scanning, still readable

Markdown holds the context, YAML holds the config. Edit any of it with a text editor; the server reads the files on demand, so changes apply immediately. Two exceptions load at server start and need a restart to pick up edits:agent.mdand command files.

At connect, every agent receives two layers of instructions: gcontext's fixed instructions (shipped with the package, they explain the tools and folder conventions), then youragent.md(what this particular agent is). You only ever write the second layer.

Connected clients get seven tools:read_file,write_file,list_dir,grep,run_script,run_adhoc_script,agent. Every state file is also exposed as an MCP resource atgcontext://<path>, so runtimes that support resource mentions can attach a file directly, e.g.@my-agent:gcontext://modules/topic/index.md.

initcreates no connections: a connection is worth having when it points at a service you actually use. Adding one is three files, no command needed:

connections/stripe/connection.yamldeclares what the connection needs, by name only:

name: stripe description: Payments, test mode. secrets: - STRIPE_API_KEY deps: - stripe

Put the value insecrets.env(gitignored, never leaves your machine):

echo 'STRIPE_API_KEY=sk_test_...' >> my-agent/secrets.env

And writeconnections/stripe/index.md: what the service is for, which endpoints matter, any usage patterns worth remembering. The agent reads this before writing scripts, and updates it as it learns.

That's it. The server picks the connection up on the next tool call (no restart),gcontext statusshows whether every declared secret has a value, and the agent can now call the API throughrun_adhoc_scriptandrun_scriptwithout ever seeing the key.

The full reference is in docs/connections.md.

Pre-built agents live in the bleak-ai/agentsregistry. Install one with:

This copies the agent's modules, connections, and commands into your state folder. Agents that depend on other agents are resolved recursively. To create and share your own agent, see docs/share-agent.md.

- examples/ops-agent- a complete agent folder with connections, modules, a command, and an archived module
- docs/design.md- why gcontext is built this way, decision by decision
- docs/connections.md- the connection reference, from manifest fields to smoke tests
- docs/modules.md- writing portable, shareable modules
- docs/agents.md- the agent template standard for distributable agents
- docs/setup-script.md- the setup script standard, every text a user reads during install and setup
- docs/share-agent.md- turning a lived agent into a shareable template
- docs/reference.md- secrets, commands, dashboard, archiving, context ledger, controlled sessions

Local only. The server binds127.0.0.1without auth, so it is not reachable from outside your machine and should stay that way. A remote variant (same model, URL plus token) is planned but not part of this release.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Create crafted UI components inspired by the best 21st.dev design engineers.

Bring agent evaluations, observability, and synthetic test set generation directly into your IDE for free with Galileo's new MCP server

An MCP server to help AI assistants to answer questions and generate AccelByte Extend SDK code more effectively .

MCP server for AI Diagram Maker — generate beautiful software engineering diagrams directly inside Cursor, Claude Desktop, Claude Code, or any MCP-compatible AI agent

ALAPI MCP Tools,Call hundreds of API interfaces via MCP

AI-powered SVG animation generator that transforms static files into animated SVG components using the Allyson platform

MCP server that gives AI assistants on-demand access to 1,500+ amCharts docs, ~300 code examples, and 1000+ class API references.

APIMatic MCP Server is used to validate OpenAPI specifications using APIMatic. The server processes OpenAPI files and returns validation summaries by leveraging APIMatic’s API.

One shared context layer for AI agents and humans — live API specs, DB schemas, and versioned contracts across repos so every agent and teammate works from the same source of truth.

Build and deploy full-stack Next.js apps with 98 tools for React, AWS, and MongoDB

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

Claude Desktop / Cursor

Type

Command

Args

Env

Install

More like this

Time

Sentry

Github

Git

GitLab

Context 7