resemble-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RESEMBLE_API_KEY | Yes | API key for Resemble AI authentication, used as a Bearer token for the API. |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| resemble_list_detect_agentsA | List Resemble Detect Agents available to this API key (managed authenticity investigators). |
| resemble_run_investigationB | Run a Detect Agent investigation on a public media/page URL or local file. Prefer url. agent_uuid comes from resemble_list_detect_agents (e.g. investigate_social_content, verify_breaking_news, verify_document, website_check). Optional query is the investigation objective. Consumes the SSE stream and returns run_id, final verdict/intelligence, and a transcript excerpt. |
| resemble_list_investigation_runsB | List recent investigation runs for a Detect Agent. |
| resemble_get_investigation_runB | Fetch a persisted Detect Agent investigation run by run_id. |
| resemble_create_detectionA | Submit a deepfake detection job for audio, image, or video. Provide exactly one of url (public HTTPS) or file_path. wait=True sends Prefer: wait so the response includes a completed verdict when possible. Optional intelligence / watermark / source-tracing / reverse-search flags map to the Detect API. |
| resemble_get_detectionA | Get a deepfake detection result by UUID. Set experts=true for all completed Intelligence results. |
| resemble_ask_detection_questionC | Ask a natural-language question about a completed Detect report (Detect Intelligence). |
| resemble_get_detection_answerC | Poll the answer for a Detect Intelligence question. |
| resemble_secure_uploadB | Upload private media to Resemble and return a short-lived media_token (1 hour) for Detect. |
| resemble_accountA | Sanity-check the API key by fetching the Resemble account profile. |
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 10 tools
Each tool maps to a distinct phase of the Detect workflow: account check, upload, detection submission/retrieval, intelligence Q&A, and agent investigations. Even the paired ask/get answer tools are clearly separated by their roles. No two tools appear to do the same thing.
Most tools follow a clear resemble_verb_noun pattern, such as resemble_list_detect_agents and resemble_get_investigation_run. A few exceptions like resemble_account and resemble_secure_upload break the verb-first convention, but overall the naming remains predictable and readable.
Ten tools is a well-scoped size for a deepfake detection server. Each tool covers a necessary capability without redundancy, and the count fits comfortably within the ideal range for a focused MCP server.
The surface covers account verification, secure uploads, detection submission and retrieval, intelligence Q&A, and the full investigation run lifecycle. The only notable gap is the lack of a way to list all detection jobs, which agents can work around by tracking UUIDs themselves.