Primateintelligence

ai.primateintelligencePublished by primateintelligence.aiOfficial publisherv0.4.0Updated Oct 25, 2026

Video scene understanding for AI agents via the Primate Vision API.

VerifiedStreamable HTTPWeb executableData & AnalyticsMedia & DesignAI & ML

Overview

AI-generated overview

Primate Vision MCP server that lets an assistant register videos and ask plain-English questions about their scenes, returning yes/no/indeterminate answers with

What you can do
Register a video from a public https URL and list available models or a test fixture for verification. Validate a question as a free dry run with an assessability check and cost estimate. Create single or batch analyses (2–10 prompts on one video) and poll until a terminal state. Read results: answer, confidence, clip timestamps, detected counts and indeterminate reason. Check credit balance, usage meters and the per-analysis transaction ledger.
When to use it
Useful when an assistant needs deterministic, evidence-backed answers about what happens in a video — for example checking whether a person or object appears — rather than free-form descriptions. Also suited to agents that want to self-verify an integration and preview costs before spending credits.
Requirements
Either the remote streamable HTTP endpoint with OAuth sign-in (no install, no key handling), or the local npm package run via npx over stdio. The local mode requires the PRIMATE_API_KEY environment variable; an optional PRIMATE_BASE_URL overrides the default endpoint. Network access to the Primate Vision API is needed.
Before you install
Analyses consume paid credits; batch prompts after the first are billed at 50%, and insufficient_credits errors point to billing. The local mode needs a live API key in PRIMATE_API_KEY, which the README says is read only from the environment and never accepted as a tool argument. Registering a video sends its public URL to the Primate Vision API. No tool deletes data.

Installation

In SourceWeft

  1. Open Primateintelligence in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/ai.primateintelligence%2Fmcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "primateintelligence": {
      "type": "http",
      "url": "https://api.primateintelligence.ai/mcp"
    }
  }
}

README

@primate-intelligence/mcp

[npm] [license]

MCP (Model Context Protocol) server for the Primate Vision video analysis API — a video understanding API by Primate Intelligence (docs · llms.txt).

Gives AI agents video scene understanding as 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 is yes / no / indeterminate with evidence.

Try it for free

A free test key requires no email, no card, no signup:

bash
curl -X POST https://api.primateintelligence.ai/v1/sandbox

Your AI agent can do this for you — right from Claude. Point it at primateintelligence.ai/llms.txt and it can discover, provision, integrate, and self-verify with zero human steps.

Two ways to connect

1. Remote server (recommended) — OAuth, nothing to install

Streamable HTTP endpoint with full OAuth 2.1 + Dynamic Client Registration + PKCE:

https://api.primateintelligence.ai/mcp

In Claude.ai / Claude Desktop: Settings → Connectors → Add custom connector, paste the URL, sign in. No API key handling — the OAuth flow issues and rotates tokens for you.

2. Local stdio server

jsonc
// 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_…" }    }  }}

Tools

ToolDoesRead-only
create_video_from_urlRegister a video from a public https URL (POST /v1/videos)—
create_analysisAsk a question about a video (POST /v1/analyses)—
validate_analysisDry-run a prompt: assessability + cost estimate, zero credits (validate_only: true)✓
create_analysis_batch2–10 prompts on one video; each after the first billed at 50% (POST /v1/analyses/batch)—
get_analysisFetch analysis status/result (GET /v1/analyses/{id})✓
wait_for_analysisPoll until terminal state; returns { analysis, retry }✓
list_modelsList available models (GET /v1/models)✓
get_usageCredit balance + period meters (GET /v1/usage)✓
get_creditsBalance + per-analysis transaction ledger (GET /v1/credits)✓
get_test_fixtureStable fixture for integration self-verification (GET /v1/test-fixture)✓

Every tool carries MCP annotations (title, readOnlyHint, destructiveHint, idempotentHint, openWorldHint), declares an outputSchema, and returns structuredContent conforming to it. No tool deletes data. Tool descriptions and schemas mirror the OpenAPI document at GET /v1/openapi.json — the spec is the source of truth.

Typical agent flow

  1. get_test_fixture → verify the integration works (test keys return deterministic results, no quota burn)
  2. create_video_from_url with the video URL
  3. validate_analysis → confirm the prompt is assessable + preview estimated_cost_usd (free)
  4. create_analysis with the question — "Is there a person in this video?" — or create_analysis_batch for several
  5. wait_for_analysis → result.answer (yes | no | indeterminate) + result.confidence + result.clips + result.detected_count (count queries) + result.indeterminate_reason
  6. On insufficient_credits: call get_credits, report the balance + recent debits, point the human at billing

Security contract

The API key is read from the PRIMATE_API_KEY environment 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 error code, a docs_url, and the request_id so an agent can self-correct without a human in the loop.

Configuration

VarRequiredDefault
PRIMATE_API_KEYyes—
PRIMATE_BASE_URLnohttps://api.primateintelligence.ai

Development

bash
npm installnpm test        # vitest — tool surface, security contract, polling, error shapenpm run build   # tsc → dist/

Links

License

MIT © Primate AI, Inc.

Source: README.md at commit 0cfd58d

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v0.4.0LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts