ContextECF MCP
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CONTEXTECF_ENDPOINT | No | The base URL of the Fabric public API. | |
| CONTEXTECF_MCP_PATH | No | Path for the HTTP MCP endpoint (when transport is http). | /mcp |
| CONTEXTECF_MCP_PORT | No | Port for the HTTP MCP server (when transport is http). | 3001 |
| CONTEXTECF_AUTH_MODE | No | Authentication mode: 'oidc' (using access token) or 'api_key' (using client credentials). | |
| CONTEXTECF_CLIENT_ID | No | Client ID for API key authentication (required when CONTEXTECF_AUTH_MODE=api_key). | |
| CONTEXTECF_TENANT_ID | No | The tenant identifier for the Fabric instance. | |
| CONTEXTECF_ACCESS_TOKEN | No | Access token for OIDC authentication (required when CONTEXTECF_AUTH_MODE=oidc). | |
| CONTEXTECF_CLIENT_SECRET | No | Client secret for API key authentication (required when CONTEXTECF_AUTH_MODE=api_key). | |
| CONTEXTECF_MCP_TRANSPORT | No | Transport mode for the MCP server (e.g., 'http' for Streamable HTTP). | stdio |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| context_assembleB | Assemble a read-only governed ContextECF context package with a synthetic assembled-context preview, selected sources, exclusions, metadata-only evidence references, sufficiency, gaps, and receipt metadata. |
| context_explainB | Explain public context package assembly metadata. |
| context_evidenceA | Return metadata for a public evidence reference. |
| context_statusA | Check ContextECF MCP facade readiness. |
| context_feedbackC | Submit metadata-only feedback about context package usefulness. |
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 5 tools
Each tool has a clearly distinct purpose: assembling packages, explaining package metadata, fetching evidence metadata, checking server readiness, and submitting feedback. There is no meaningful overlap or ambiguity between the five tools.
All tools share the consistent 'context_' prefix and use snake_case, which is helpful. However, the second part mixes verbs (assemble, explain) with nouns (evidence, status, feedback), so the naming convention is not uniformly verb-driven.
Five tools is a well-scoped size for this server's purpose. Each tool contributes a distinct capability, and the count feels neither bloated nor thin.
The core workflow of assembling, explaining, and referencing context package metadata is covered, along with status and feedback. A minor gap is the lack of a listing or search tool for discovering available public packages or evidence references, but this does not break the main use case.