Primate Intelligence MCP — Watchlist

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Follow-up value is specific to Primate video scene analysis with timestamps and confidence: Do indeterminate results retain evidence clips rather than being presented as verified binary answers?

Reviewed Oct 5, 2026 · Documentation review; complete setup workflow not independently tested

Best fit

Evidence-oriented video scene analysis with yes/no/indeterminate answers, confidence and clip timestamps.

What we know

Official Primate Vision MCP. It registers public videos, validates questions/costs, runs video analyses/batches and returns structured results with confidence, clips and indeterminate reasons. Remote OAuth and local API-key modes are supported.

Maintenance / activity evidence

@primate-intelligence/mcp 0.4.0 published 2026-08-01T21:41:40.739Z

Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: high.

Verification gaps / watch-outs

Installation and comprehensive security have not been independently audited.
Register video and create billable analysis jobs; read results/usage. Writes: Register video resource; Submit paid analysis jobs.
OAuth or API key.
Sensitive access: Video content/URLs, Analysis questions, Account credits

Primary operational risks are media confidentiality and spend.

Full authority, access and evidence limits are available in Review context and Access & risk.

All limitations / Review context

Do indeterminate results retain evidence clips rather than being presented as verified binary answers?

The bounded review of the publisher's documented Primate video scene analysis with timestamps and confidence and release notices identified no disclosed material condition preventing an accurately scoped public tracking entry. The resource's operational permissions remain uncertainty; this assessment does not certify installation safety.

Primary operational risks are media confidentiality and spend.
Register video and create billable analysis jobs; read results/usage.
OAuth or API key.
Video URLs/questions/results are processed by Primate Intelligence.
Reviewed write actions: Register video resource; Submit paid analysis jobs
Sensitive access: Video content/URLs, Analysis questions, Account credits
Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited.
Documented tool authority and any remote data handling must be checked before installation or use.
Tool inventory, client matrix and permissions completeness were not requirements for this Radar tracking review.
Analysis jobs consume credits.
Input videos are remote/public-URL based in this MCP surface.
Answers are intentionally constrained rather than free-form, but still depend on model/API performance.
No deletion tools are exposed.

Original activity observations

@primate-intelligence/mcp 0.4.0 published 2026-08-01T21:41:40.739Z

Technical identity

npm/@primate-intelligence/mcp

Exact implementation source: https://www.npmjs.com/package/@primate-intelligence/mcp ↗
Reviewed resource type: MCP Server
Repository identity: Primate-Intelligence/primate-intelligence-mcp
Package identity: npm:@primate-intelligence/mcp
Service endpoint: https://api.primateintelligence.ai/mcp

Evidence & Sources

Evidence basis: Recorded source evidence
Setup runtime verification: Not independently runtime-tested by MCP100 for this setup workflow.

Reviewed Oct 5, 2026 · Latest source observation Oct 8, 2026

Package registry ↗
@primate-intelligence/mcp
Recorded package identity, distribution or download evidence.
Includes references whose attribution is not established.

Setup · Watchlist

Install & Agents

Publisher instructions.

Source evidence observed Oct 14, 2026.

Additional setup details required — see the specific gaps below.

Install / connect
Publisher instructions
Publisher recommends hosted OAuth remote; local stdio requires PRIMATE_API_KEY.
publisher install or stdio launch · Publisher instructions
npx -y @primate-intelligence/mcp
Configure / authenticate
MCP100 setup guide
Preferred remote https://api.primateintelligence.ai/mcp with OAuth2+PKCE. Local npx stdio requires PRIMATE_API_KEY; optional PRIMATE_BASE_URL. Do not put key in tool arguments.
Previously reviewed client configuration / prerequisites: Preferred hosted endpoint uses OAuth 2.1 + PKCE + DCR;
claude desktop or cursor mcpServers json · MCP100 composed guide
{ "mcpServers": { "primate-intelligence": { "args": [ "-y", "@primate-intelligence/mcp" ], "command": "npx", "env": { "PRIMATE_API_KEY": "pv_live_REPLACE" } } } }
Check connection
Suggested check
Use publisher get_test_fixture (deterministic test fixture) or list_models/get_usage (read-only), not create_analysis (billable) or video registration.
Remove / uninstall / revoke
MCP100 setup guide
If you added this integration to Claude Code under the registration name `primate-intelligence`, run `claude mcp remove primate-intelligence` to unregister that client entry. In Claude Desktop, Cursor, VS Code or another host, delete/disable the corresponding named MCP registration in that host's settings and restart/reconnect. If you installed an npm package globally or operate a separate HTTP server, uninstall/stop it with its original deployment method. This does not delete user data or revoke service credentials.
MCP client unregister, stopping hosted processes, package uninstall, OAuth disconnect and token revocation are distinct actions.
A claude mcp remove command is only valid for Claude Code when the local registration actually has that name. Other MCP hosts require their own UI/config cleanup.
Separate credential guidance / limitations: Primate Intelligence remote MCP is OAuth, local stdio uses PRIMATE_API_KEY. Publisher README docs/agents and docs give no precise grant/key revoke UI; do not confuse free sandbox issuance with a revoke action.
Remove client registration · Claude Code only · MCP100 composed guide
claude mcp remove primate-intelligence

Official Documentation & Sources

What it does

Official Primate Vision MCP. It registers public videos, validates questions/costs, runs video analyses/batches and returns structured results with confidence, clips and indeterminate reasons. Remote OAuth and local API-key modes are supported.

Capability: AI & Reasoning
Resource type: MCP Server
Industry: Media & Marketing
Best fit: Evidence-oriented video scene analysis with yes/no/indeterminate answers, confidence and clip timestamps.

Representative uses

Register video from public URL
Validate whether a question is assessable and preview cost
Run one/batch video analysis
Poll results and inspect usage/credits

Limitations

Analysis jobs consume credits.
Input videos are remote/public-URL based in this MCP surface.
Answers are intentionally constrained rather than free-form, but still depend on model/API performance.
No deletion tools are exposed.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: OAuth or API key.
Permissions: Register video and create billable analysis jobs; read results/usage.
Data handling: Video URLs/questions/results are processed by Primate Intelligence.
Cost: usage_based
Risk and cautions: Primary operational risks are media confidentiality and spend.

Access scope and cautions

Write actions: Register video resource Submit paid analysis jobs
Sensitive access: Video content/URLs Analysis questions Account credits
Risk level: moderate

FAQ

Based on reviewed evidence as of 2026-10-08. Watchlist tracking is not a recommendation or a security certification.

Which tasks are documented for this implementation?

The reviewed tasks include: Register video from public URL; Validate whether a question is assessable and preview cost; Run one/batch video analysis; Poll results and inspect usage/credits.

What setup and authentication are documented?

Recorded installation/entrypoint step: npx -y @primate-intelligence/mcp. Recorded endpoint: https://api.primateintelligence.ai/mcp. Recorded transport: stdio, streamable_http. Recorded environment-variable notes: PRIMATE_API_KEY (local); PRIMATE_BASE_URL (optional). No configuration values are supplied here. Prerequisites: MCP client. These are the documented setup details, not a claim that installation or client compatibility was independently tested. Authentication: Remote OAuth 2.1/PKCE/DCR or local `PRIMATE_API_KEY`.

Can it modify data or perform write operations?

Documented write actions include: Register video resource; Submit paid analysis jobs. Recorded permission boundary: Register video and create billable analysis jobs; read results/usage.

What data-handling boundary should I consider?

Video URLs/questions/results are processed by Primate Intelligence. Recorded sensitive-access context: Video content/URLs; Analysis questions; Account credits.

What limitations and risks should I check before use?

Primary operational risks are media confidentiality and spend. Analysis jobs consume credits. Input videos are remote/public-URL based in this MCP surface. Answers are intentionally constrained rather than free-form, but still depend on model/API performance. No deletion tools are exposed. Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited. Documented tool authority and any remote data handling must be checked before installation or use.

What cost model is recorded?

The reviewed cost model is usage based. This classification does not establish current prices, quotas or the cost of every downstream operation. Check the applicable service terms before authorizing paid actions.