ChatGPT Context Bridge
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CONTEXT_BRIDGE_DATA_DIR | No | Directory for staging data. If not set, may use a default. | |
| CONTEXT_BRIDGE_IMPORT_ROOTS | No | Comma-separated paths to import roots. |
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 |
|---|---|
| search_contextA | Search private Context Bridge staging records. Read-only. Returns staged chat IDs, titles, summaries, and draft paths when present. |
| stage_chatA | Read a local ChatGPT export JSON or manual markdown chat file, redact sensitive values, classify it, and write only staging artifacts. Does not write to Homebase or Notion. |
| summarize_threadA | Return the deterministic summary, action candidates, and risk notes for one staged chat ID. Read-only. |
| propose_homebase_noteA | Create a staged Homebase markdown draft and suggested canonical path for one staged chat. Draft-only; no Homebase repo writes. |
| propose_notion_pageA | Create a staged Notion payload with verification notes for one staged chat. Draft-only; no Notion API calls or page mutations. |
| generate_image_assetA | Generate an image with OpenAI image generation, save it into Context Bridge staging, and return the local staged file path plus manifest metadata. Requires OPENAI_API_KEY. Does not publish media. |
| register_image_assetA | Stage image-generation artifacts by recording prompt, source chat, usage-rights note, and optional local copied asset. Does not publish media. |
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 7 tools
Most tools target distinct resources and actions: search, stage, summarize, propose for different targets, and image generation/registration. The only mild overlap is between generate_image_asset and register_image_asset, but their descriptions clarify one creates new images while the other records existing artifacts.
All tool names follow a consistent verb_noun pattern using snake_case (e.g., search_context, stage_chat, propose_notion_page). There are no mixed conventions or vague verbs, making the naming predictable and clear.
With 7 tools, the count is well within the ideal 3-15 range for a domain-specific bridge. Each tool serves a distinct purpose in the staging workflow, and none feel redundant.
The workflow appears to produce drafts and staged artifacts but lacks any publish/commit operation to actually push to Homebase or Notion. Additionally, there are no update or delete tools for staged records, creating dead ends and leaving the lifecycle incomplete.