Primate Intelligence
About
Real-time video analysis for AI agents — submit a video URL, ask a question in plain English, get a deterministic yes/no answer with confidence score and clip timestamps.
Details
- Author
- primate-intelligence
- Categories
- Other
Jump to
1. Remote server (recommended) — OAuth, nothing to install
Streamable HTTP endpoint with full OAuth 2.1 + Dynamic Client Registration + PKCE:
// claude_desktop_config.json · .mcp.json · mcp.json · .cursor/mcp.json { "mcpServers": { "primate-intelligence": { "command": "npx", "args": ](https://primateintelligence.ai/llms.txt)["-y", "@primate-intelligence/mcp"], "env": { "PRIMATE_API_KEY": "pv_live_…" } } } }
Every tool carries MCP annotations (title,readOnlyHint,destructiveHint,idempotentHint,openWorldHint), declares anoutputSchema, and returnsstructuredContentconforming to it. No tool deletes data. Tool descriptions and schemas mirror the OpenAPI document atGET /v1/openapi.json— the spec is the source of truth.
- get_test_fixture→ verify the integration works (test keys return deterministic results, no quota burn)
- create_video_from_urlwith the video URL
- validate_analysis→ confirm the prompt is assessable + previewestimated_cost_usd(free)
- create_analysiswith the question —"Is there a person in this video?"— orcreate_analysis_batchfor several
- wait_for_analysis→result.answer(yes|no|indeterminate) +result.confidence+result.clips+result.detected_count(count queries) +result.indeterminate_reason
- Oninsufficient_credits: callget_credits, report the balance + recent debits, point the human at billing
The API key is read from thePRIMATE_API_KEYenvironment variable only.No tool accepts a key, token, or secret as an argument— so credentials never land in agent transcripts, tool-call logs, or model context. This is enforced by a unit test that fails the build if any tool schema grows a credential-shaped parameter.
Errors surface the machine-readable errorcode, adocs_url, and therequest_idso an agent can self-correct without a human in the loop.
npm install npm test # vitest — tool surface, security contract, polling, error shape npm run build # tsc → dist/
- Quickstart for AI agents— the zero-human-intervention integration path
- API docs
- OpenAPI 3.1 spec
- Error registry
- llms.txt— machine-readable index for agents
- Privacy policy·Terms
An MCP server for AI video generation. MCP server for AI video generation. Lets Claude, ChatGPT, OpenClaw , Hermes & other agents create AI videos and publish them to YouTube, TikTok, Instagram etc..
An Ai Video Agent that can generate professional and complex videos with simple prompts and context images.
The TwelveLabs MCP Server provides seamless integration with the TwelveLabs platform. This server enables AI assistants and applications to interact with TwelveLabs powerful video analysis capabilities through a standardized MCP interface.
API for AI agents to search, license, and download b-roll video clips and voiceovers. Pay-per-request, no human interaction required.
All-in-one AI creative studio — generate videos, images, audio in 11 Indian languages, and 3D models via MCP. Hosted at mcp.arcframe.ai.
34-tool MCP server for CutPro's v1 API — analyze videos, clip, render, and publish posts via AI clients like Claude, ChatGPT, and Cursor.
A server for creating fast and free lipsync videos for digital avatars, supporting both realistic and cartoon styles.
Multimodal cultural intelligence MCP server that analyzes text, images, and video for cultural risks across 200+ markets with 9 specialized tools.
Automate end-to-end youtube production pipeline for face less channels
Licensed AI content access. 1,821 Dhar Mann Studios videos. $0.0025/pull, creator compensated automatically. 30ms delivery.
MCP (Model Context Protocol) server for thePrimate Vision video analysis API— a video understanding API byPrimate Intelligence(docs·llms.txt).
Gives AI agentsvideo scene understandingas tools: register a video, ask a question in plain English, get a deterministic answer with a confidence score and clip timestamps. No hallucinated descriptions — the answer isyes/no/indeterminatewith evidence.
A free test key requires no email, no card, no signup:
curl -X POST https://api.primateintelligence.ai/v1/sandbox
Your AI agent can do this for you — right from Claude. Point it atprimateintelligence.ai/llms.txtand it can discover, provision, integrate, and self-verify with zero human steps.
1. Remote server (recommended) — OAuth, nothing to install
Streamable HTTP endpoint with full OAuth 2.1 + Dynamic Client Registration + PKCE:
// claude_desktop_config.json · .mcp.json · mcp.json · .cursor/mcp.json { "mcpServers": { "primate-intelligence": { "command": "npx", "args": ["-y", "@primate-intelligence/mcp"], "env": { "PRIMATE_API_KEY": "pv_live_…" } } } }
Every tool carries MCP annotations (title,readOnlyHint,destructiveHint,idempotentHint,openWorldHint), declares anoutputSchema, and returnsstructuredContentconforming to it. No tool deletes data. Tool descriptions and schemas mirror the OpenAPI document atGET /v1/openapi.json— the spec is the source of truth.
- get_test_fixture→ verify the integration works (test keys return deterministic results, no quota burn)
- create_video_from_urlwith the video URL
- validate_analysis→ confirm the prompt is assessable + previewestimated_cost_usd(free)
- create_analysiswith the question —"Is there a person in this video?"— orcreate_analysis_batchfor several
- wait_for_analysis→result.answer(yes|no|indeterminate) +result.confidence+result.clips+result.detected_count(count queries) +result.indeterminate_reason
- Oninsufficient_credits: callget_credits, report the balance + recent debits, point the human at billing
The API key is read from thePRIMATE_API_KEYenvironment variable only.No tool accepts a key, token, or secret as an argument— so credentials never land in agent transcripts, tool-call logs, or model context. This is enforced by a unit test that fails the build if any tool schema grows a credential-shaped parameter.
Errors surface the machine-readable errorcode, adocs_url, and therequest_idso an agent can self-correct without a human in the loop.
npm install npm test # vitest — tool surface, security contract, polling, error shape npm run build # tsc → dist/
- Quickstart for AI agents— the zero-human-intervention integration path
- API docs
- OpenAPI 3.1 spec
- Error registry
- llms.txt— machine-readable index for agents
- Privacy policy·Terms
An MCP server for AI video generation. MCP server for AI video generation. Lets Claude, ChatGPT, OpenClaw , Hermes & other agents create AI videos and publish them to YouTube, TikTok, Instagram etc..
An Ai Video Agent that can generate professional and complex videos with simple prompts and context images.
The TwelveLabs MCP Server provides seamless integration with the TwelveLabs platform. This server enables AI assistants and applications to interact with TwelveLabs powerful video analysis capabilities through a standardized MCP interface.
API for AI agents to search, license, and download b-roll video clips and voiceovers. Pay-per-request, no human interaction required.
All-in-one AI creative studio — generate videos, images, audio in 11 Indian languages, and 3D models via MCP. Hosted at mcp.arcframe.ai.
34-tool MCP server for CutPro's v1 API — analyze videos, clip, render, and publish posts via AI clients like Claude, ChatGPT, and Cursor.
A server for creating fast and free lipsync videos for digital avatars, supporting both realistic and cartoon styles.
Multimodal cultural intelligence MCP server that analyzes text, images, and video for cultural risks across 200+ markets with 9 specialized tools.
Automate end-to-end youtube production pipeline for face less channels
Licensed AI content access. 1,821 Dhar Mann Studios videos. $0.0025/pull, creator compensated automatically. 30ms delivery.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
