Which integrations are available for this server?

Enables context compression and formatting for Gemini (Google), allowing seamless continuation of conversations. Enables context compression and formatting for ChatGPT (OpenAI), allowing seamless continuation of conversations.

How do I use ContextBridge?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@ContextBridge compress this conversation about project planning for handoff to ChatGPT" 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.

ContextBridge

by prateekg7

Overview Schema Related Servers Score Discussions

TypeScript

Remote

ContextBridge

npm version MCP Registry

ContextBridge is a context portability tool for AI conversations. This package publishes the MCP server surface: it compresses an in-progress conversation into a structured context block that preserves the user's goal, confirmed decisions, current state, open threads, artifacts, constraints, recent pivots, and suggested next step, then formats that handoff so another AI can continue without forcing the user to restate everything.

The published npm artifact is the stdio MCP server for Claude Desktop, agent runtimes, and other MCP-compatible hosts. The browser extension runtime is developed in the same repository, but it is not part of this MCP Registry publishing flow.

Published Links

npm package: @contextbridge_ai/mcp
MCP Registry search: io.github.prateekg7/context-bridge
MCP Registry API: latest version JSON
Source repository: prateekg7/Context-Bridge

Related MCP server: Memory MCP Server

Install In Claude Desktop

Add this to your Claude Desktop MCP config (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "contextbridge": {
      "command": "npx",
      "args": ["-y", "@contextbridge_ai/mcp"],
      "env": {
        "GROQ_API_KEY": "your_groq_api_key_here"
      }
    }
  }
}

Or with OpenAI:

{
  "mcpServers": {
    "contextbridge": {
      "command": "npx",
      "args": ["-y", "@contextbridge_ai/mcp"],
      "env": {
        "OPENAI_API_KEY": "your_openai_api_key_here",
        "OPENAI_MODEL": "gpt-4.1-mini"
      }
    }
  }
}

For a hosted no-key lane instead of BYOK:

{
  "mcpServers": {
    "contextbridge": {
      "command": "npx",
      "args": ["-y", "@contextbridge_ai/mcp"],
      "env": {
        "CONTEXTBRIDGE_HOSTED_URL": "https://your-hosted-endpoint.example/v1",
        "CONTEXTBRIDGE_HOSTED_MODEL": "mistralai/Mistral-7B-Instruct-v0.2"
      }
    }
  }
}

Available MCP Tools

`compress_context`

Compresses a raw transcript into a structured context block.

Parameters:

transcript (string, required): the raw conversation transcript to compress.
provider ("openai" | "openai-chat" | "google" | "groq" | "custom" | "hosted", optional): provider override.
model (string, optional): model override for the selected lane.
apiKey (string, optional): BYOK API key override.
baseUrl (string, optional): API base URL override.
hostedApiKey (string, optional): optional auth key for the hosted lane.

`format_for_target`

Formats a compressed context block for a destination platform.

Parameters:

context_block (object, required): a validated ContextBridge compressed context block.
target ("claude" | "chatgpt" | "gemini", required): destination AI platform.

`resume_context`

Builds a destination-ready landing package from a compressed context block.

Parameters:

context_block (object, required): a validated ContextBridge compressed context block.
target ("claude" | "chatgpt" | "gemini", required): destination AI platform.

BYOK Setup

ContextBridge auto-selects the OpenAI Responses lane when a BYOK key is present.

Environment variables:

OPENAI_API_KEY=your_openai_api_key_here
OPENAI_MODEL=gpt-4.1-mini
OPENAI_BASE_URL=https://api.openai.com/v1

Additional supported provider overrides:

GOOGLE_API_KEY=your_google_api_key_here
GOOGLE_MODEL=gemini-2.5-pro
GOOGLE_BASE_URL=https://generativelanguage.googleapis.com/v1beta/openai

GROQ_API_KEY=your_groq_api_key_here
GROQ_MODEL=llama-3.3-70b-versatile
GROQ_BASE_URL=https://api.groq.com/openai/v1

CONTEXTBRIDGE_API_KEY=your_custom_api_key_here
CONTEXTBRIDGE_MODEL=your_custom_model_here
CONTEXTBRIDGE_BASE_URL=https://your-endpoint.example/v1
CONTEXTBRIDGE_PROVIDER=custom

Hosted Lane Setup

The hosted lane is the no-key path for end users who do not bring their own provider credentials.

Environment variables:

CONTEXTBRIDGE_HOSTED_URL=https://your-hosted-endpoint.example/v1
CONTEXTBRIDGE_HOSTED_MODEL=mistralai/Mistral-7B-Instruct-v0.2
CONTEXTBRIDGE_HOSTED_API_KEY=

Selection priority:

Explicit apiKey option passed into compression uses the OpenAI Responses BYOK lane.
OPENAI_API_KEY uses the OpenAI Responses BYOK lane.
CONTEXTBRIDGE_HOSTED_URL uses the hosted lane.

Contributing

Contributions are welcome. The highest-leverage areas are extraction quality evaluation, browser collector resilience, destination formatting quality, hosted-lane infrastructure, and real-world handoff testing across platforms.

License

MIT. See LICENSE.

Available Tools

4 tools

compress_contextCompress ContextA

Read-onlyIdempotent

Compresses a raw conversation transcript into a structured ContextBridge handoff block.

ParametersJSON Schema

Name	Required	Description	Default
`provider`	No	Optional provider override for the extraction lane: openai, openai-chat, google, groq, custom, or hosted.
`transcript`	Yes	The raw conversation transcript to compress.

Output Schema

ParametersJSON Schema

Name	Required	Description
`goal`	Yes	The user's primary goal as of the latest meaningful state in the transcript.
`version`	Yes	Schema version for ContextBridge output.
`open_threads`	Yes	Unresolved work, risks, or follow-ups that still need attention.
`recent_pivot`	Yes
`current_state`	Yes	A concise description of where the work currently stands, weighted toward the final 25% of the conversation.
`key_artifacts`	Yes	Important outputs, files, prompts, or assets mentioned in the transcript.
`decisions_made`	Yes	Only decisions explicitly confirmed, chosen, or accepted by the user. Suggestions alone do not count.
`conversation_type`	Yes	The dominant type of work the conversation is doing.
`suggested_next_step`	Yes	The best immediate next action for continuing the conversation.
`user_expertise_level`	Yes	Estimated expertise level implied by the user's language and requests.
`conversation_assessment`	Yes
`constraints_and_preferences`	Yes	Important user preferences, constraints, or non-negotiables.

TDQS

A3.7/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, which cover behavioral traits. The description adds minimal extra context, only specifying the output format (ContextBridge handoff block), which is useful but not behavioral.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence of 11 words, efficiently stating the tool's purpose. It is front-loaded with the verb.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple tool with 2 parameters, full schema coverage, and an output schema present, the description is complete enough for an agent to understand the tool's function.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already describes both parameters with 100% coverage. The description does not add any parameter-specific information beyond what is in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'compresses' and the resource 'raw conversation transcript' and the outcome 'structured ContextBridge handoff block'. This distinguishes it from siblings like say_hello and resume_context.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus its siblings (say_hello, format_for_target, resume_context). There is no mention of prerequisites, alternatives, or when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

format_for_targetFormat For TargetA

Read-onlyIdempotent

Formats a compressed ContextBridge handoff block into a paste-ready opening prompt for a destination AI platform.

ParametersJSON Schema

Name	Required	Description	Default
`target`	Yes	The destination platform: claude, chatgpt, or gemini.
`context_block`	Yes	The structured ContextBridge handoff block to format.

Output Schema

ParametersJSON Schema

Name	Required	Description
`target`	Yes	The destination AI platform.
`api_split`	Yes
`format_version`	Yes	Schema version for formatted prompt output.
`formatted_prompt`	Yes	A paste-ready opening message for the target platform.
`usage_instructions`	Yes	How to use this formatted output on the target platform.
`prompt_structure_notes`	Yes	Why this format was chosen for the target platform.

TDQS

A3.8/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and idempotentHint true. The description adds no further behavioral traits, but does not contradict annotations. No contradiction detected.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, no redundancy, front-loaded with key action. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complex nested context_block and output schema exists, the description is sufficient. However, it could hint at output format or constraints, but not necessary due to rich schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents both parameters thoroughly. The description adds no extra meaning beyond what's in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Formats' and the resource: 'compressed ContextBridge handoff block' into 'paste-ready opening prompt'. It distinguishes from siblings like compress_context (compression) and resume_context (resumption).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit when to use or when not to use, nor alternatives mentioned. Context implies it's for formatting compressed blocks for destination platforms, but no guidance on excluding cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

resume_contextResume ContextA

Read-onlyIdempotent

Packages a stored ContextBridge handoff block into a destination-ready landing bundle for resuming the conversation on another AI platform.

ParametersJSON Schema

Name	Required	Description	Default
`target`	Yes	The destination platform: claude, chatgpt, or gemini.
`context_block`	Yes	The structured ContextBridge handoff block to resume from.

Output Schema

ParametersJSON Schema

Name	Required	Description
`target`	Yes	The destination AI platform.
`handoff_kind`	Yes	Identifies this as a destination-side resume package.
`resume_ready`	Yes	Whether the package is ready to use immediately.
`format_version`	Yes	Schema version for resume context output.
`operator_steps`	Yes	Step-by-step instructions for using this handoff package.
`continuation_plan`	Yes	The intended first move after the receiving AI loads the handoff.
`api_resume_payload`	Yes	The split system/user payload to use when the destination supports separate instruction channels.
`usage_instructions`	Yes	A concise explanation of how to use this resume package.
`manual_resume_message`	Yes	The single paste-ready message to use when the destination only supports a single opening message.
`prompt_structure_notes`	Yes	Notes explaining why this landing package is structured this way.

TDQS

A4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is clear. The description adds context about the packaging process and destination readiness, which is useful but does not introduce new behavioral traits beyond what annotations imply.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, complete sentence with no wasted words. It is front-loaded with the action verb 'Packages' and conveys the core purpose efficiently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of the input (2 required parameters, one deeply nested with 12+ subfields), the description is concise but adequate. The presence of annotations and an output schema (not shown) reduces the burden. However, a brief note about what a 'ContextBridge handoff block' is could improve completeness for unfamiliar agents.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with detailed descriptions for each parameter (target enum with platforms, context_block with nested structure). The description does not add meaning beyond what the schema already provides, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Packages', the resource 'stored ContextBridge handoff block', and the result 'destination-ready landing bundle for resuming the conversation on another AI platform'. It distinguishes from siblings like compress_context and format_for_target by focusing on resuming, not compressing or formatting.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for resuming conversations across platforms but does not explicitly state when to use this tool versus alternatives (e.g., compress_context, format_for_target). No 'when not to use' or comparison guidance is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

say_helloSay HelloA

Dummy tool used to confirm the ContextBridge MCP server is connected and working.

ParametersJSON Schema

Name	Required	Description	Default
`name`	Yes	The name to greet

TDQS

A3.7/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden for behavioral disclosure. It labels the tool as 'dummy' implying no side effects, but does not describe output or any other behavior beyond greeting. Minimal transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that efficiently communicates the tool's purpose with no unnecessary words. It is front-loaded and appropriately sized.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple dummy tool with one parameter and no output schema, the description is complete. It adequately covers the tool's function and purpose without missing information.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for the only parameter 'name'. The schema already describes it as 'The name to greet'. The description adds no additional meaning beyond what the schema provides, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose as a dummy tool to confirm server connectivity, with a specific verb 'confirm' and resource 'ContextBridge MCP server'. It distinguishes from sibling tools (compress_context, format_for_target, resume_context) which handle different tasks.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is for testing connectivity but does not explicitly state when to use it versus alternatives like the sibling tools. No context on when not to use is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

4 tool updatesv0.1.3Jul 28, 2026
- First observedcompress_context
- First observedformat_for_target
- First observedresume_context
- First observedsay_hello

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.1/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose: health check, compression, formatting, and resume packaging. No overlap or ambiguity.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case, making them predictable and easy to understand.

Tool Count5/5

With 4 tools, the server is appropriately scoped for its purpose of context handoff, each tool is necessary and none are superfluous.

Completeness4/5

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.

Maintenance

ActivityInactive

ResponsivenessSyncing

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Native SoilOAuth
dev.nativesoil
Save an AI chat's working state, load it in any other model or provider. Verified, secret-safe.
Knowledge & Memory Agent Orchestration
2
Context Book
io.github.aditya201551
Stop re-explaining yourself to Agents. Give it the right context, right when needed.
Knowledge & Memory RAG Systems
35
PCD (Portable Context Deck)OAuth
ai.portablecontext
Your portable context layer — load it into any AI.
Knowledge & Memory RAG Systems
1
CLS++ MemoryOAuth
io.github.rajamohan1950
Cross-LLM persistent memory: store context once, recall it from any AI model.
Knowledge & Memory AI & Machine Learning
2

Related MCP Servers

snapshot-mcp-server
Knowledge & Memory Developer Tools Autonomous Agents
WhenMoon-afk
A
license
Not graded
quality
D
maintenance
Save conversation state, resume work across sessions, and organize multiple snapshots with minimal token overhead.
Updated 7 months ago (2026-01-31 07:19 UTC)
18
MIT
Memory MCP Server
Knowledge & Memory Autonomous Agents RAG Systems
stilllovee
A
license
Not graded
quality
D
maintenance
Enables AI agents to maintain context across conversation sessions by saving and retrieving summaries of key points from past interactions.
Updated 9 months ago (2025-11-29 16:02 UTC)
225
MIT
context-diamond
Knowledge & Memory Autonomous Agents Developer Tools
RainCherb
A
license
B
quality
B
maintenance
Enables LLM agents to compress handoffs into structured, auditable context capsules, preserving goals, constraints, decisions, and risks without external API calls.
Updated 3 months ago (2026-06-15 17:40 UTC)
3
20
MIT
CONTINUITY
Knowledge & Memory Developer Tools
duke-of-beans
F
license
Not graded
quality
C
maintenance
Provides session persistence, crash recovery, decision tracking, and context compression for AI assistants, enabling seamless multi-session continuity.
Updated a month ago (2026-08-10 02:45 UTC)
-

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/prateekg7/Context-Bridge'

If you have feedback or need assistance with the MCP directory API, please join our Discord server