# io.github.prateekg7/context-bridge (npm · @contextbridge_ai/mcp)

Context portability MCP server for compressing, formatting, and resuming AI conversation handoffs.

- Trust score: 67/100 (medium)
- Change this week: +21
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@contextbridge_ai/mcp`: 67/100 (this document), [markdown](https://verifymcp.io/servers/prateekg7-context-bridge/contextbridge-ai-mcp.md), [page](https://verifymcp.io/servers/prateekg7-context-bridge/contextbridge-ai-mcp)

## Channel facts

- Registry: `npm`
- Package: `@contextbridge_ai/mcp`
- Version: `0.1.3`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 82 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 240 tokens (~60/item across 4 items; 4 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (75% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add prateekg7-context-bridge -- npx -y @contextbridge_ai/mcp
```

### Codex

```bash
codex mcp add prateekg7-context-bridge -- npx -y @contextbridge_ai/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "prateekg7-context-bridge": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@contextbridge_ai/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add prateekg7-context-bridge --command npx --arg -y --arg @contextbridge_ai/mcp
```

### Hermes

```yaml
mcp_servers:
  prateekg7-context-bridge:
    command: "npx"
    args: ["-y", "@contextbridge_ai/mcp"]
```

### Other

```json
{
  "mcpServers": {
    "prateekg7-context-bridge": {
      "command": "npx",
      "args": [
        "-y",
        "@contextbridge_ai/mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 67, +4)

- [functional improvement] Stability: unverified → 0.23

### 2026-08-02 (score 63, +42)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] Dependency health: partial → unverified
- [functional regression] Security disclosure: fail → unverified
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] License: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional] Licence: MIT

### 2026-08-01 (score 21, 0)

- [security improvement] Malware scan: unverified → pass
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional] First check of Schema quality: unverified

### 2026-07-31 (score 21, −25)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (4)

### `say_hello` (~35 tokens)

Say Hello

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

Input parameters:

- `name` (string, required): The name to greet

### `compress_context` (~67 tokens)

Compress Context

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

Input parameters:

- `provider` (string): Optional provider override for the extraction lane: openai, openai-chat, google, groq, custom, or hosted.
- `transcript` (string, required): The raw conversation transcript to compress.

Output parameters:

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

### `format_for_target` (~67 tokens)

Format For Target

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

Input parameters:

- `context_block` (object, required): The structured ContextBridge handoff block to format.
- `target` (string, required): The destination platform: claude, chatgpt, or gemini.

Output parameters:

- `api_split` (object)
- `format_version` (string): Schema version for formatted prompt output.
- `formatted_prompt` (string): A paste-ready opening message for the target platform.
- `prompt_structure_notes` (array): Why this format was chosen for the target platform.
- `target` (string): The destination AI platform.
- `usage_instructions` (string): How to use this formatted output on the target platform.

### `resume_context` (~71 tokens)

Resume Context

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

Input parameters:

- `context_block` (object, required): The structured ContextBridge handoff block to resume from.
- `target` (string, required): The destination platform: claude, chatgpt, or gemini.

Output parameters:

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

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/prateekg7-context-bridge/contextbridge-ai-mcp#diagnostics

## Score history

- 2026-08-03: 67
- 2026-08-02: 63
- 2026-08-01: 21
- 2026-07-31: 21
- 2026-07-30: 46
- 2026-07-28: 46
- 2026-07-27: 46

## Links

- npm package: https://www.npmjs.com/package/@contextbridge_ai/mcp
- Socket report: https://socket.dev/npm/package/@contextbridge_ai/mcp
- Repository: https://github.com/prateekg7/Context-Bridge
- Changelog RSS feed: https://verifymcp.io/servers/prateekg7-context-bridge/contextbridge-ai-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/prateekg7-context-bridge/contextbridge-ai-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/prateekg7-context-bridge/contextbridge-ai-mcp