ContextBridge
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GROQ_MODEL | No | Groq model override. | llama-3.3-70b-versatile |
| GOOGLE_MODEL | No | Google model override. | gemini-2.5-pro |
| GROQ_API_KEY | No | Groq API key for BYOK lane. | |
| OPENAI_MODEL | No | OpenAI model override. | gpt-4.1-mini |
| GROQ_BASE_URL | No | Groq base URL. | https://api.groq.com/openai/v1 |
| GOOGLE_API_KEY | No | Google API key for BYOK lane. | |
| OPENAI_API_KEY | No | OpenAI API key for BYOK lane. | |
| GOOGLE_BASE_URL | No | Google base URL. | https://generativelanguage.googleapis.com/v1beta/openai |
| OPENAI_BASE_URL | No | OpenAI base URL. | https://api.openai.com/v1 |
| CONTEXTBRIDGE_MODEL | No | Custom model override. | |
| CONTEXTBRIDGE_API_KEY | No | Custom BYOK API key. | |
| CONTEXTBRIDGE_BASE_URL | No | Custom base URL. | |
| CONTEXTBRIDGE_PROVIDER | No | Provider identifier for custom lane. | custom |
| CONTEXTBRIDGE_HOSTED_URL | No | Hosted lane endpoint URL. | |
| CONTEXTBRIDGE_HOSTED_MODEL | No | Hosted lane model. | mistralai/Mistral-7B-Instruct-v0.2 |
| CONTEXTBRIDGE_HOSTED_API_KEY | No | Optional auth key for hosted lane. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| say_helloA | Dummy tool used to confirm the ContextBridge MCP server is connected and working. |
| compress_contextA | Compresses a raw conversation transcript into a structured ContextBridge handoff block. |
| format_for_targetA | Formats a compressed ContextBridge handoff block into a paste-ready opening prompt for a destination AI platform. |
| resume_contextA | Packages a stored ContextBridge handoff block into a destination-ready landing bundle for resuming the conversation on another AI platform. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: health check, compression, formatting, and resume packaging. No overlap or ambiguity.
All tool names follow a consistent verb_noun pattern in snake_case, making them predictable and easy to understand.
With 4 tools, the server is appropriately scoped for its purpose of context handoff, each tool is necessary and none are superfluous.
The core workflow of compressing, formatting, and resuming context is covered. A minor gap is the lack of a decompress tool for reading the stored context, but it's not essential for the stated purpose.