Skip to main content
hc
Submit
mcpSource-backed

Replicate MCP Server

Official Replicate MCP server for using Replicate model search, API tooling, and optional code-mode workflows from Claude Desktop, VS Code, Cursor, and compatible MCP clients.

by Replicate · submitted by JSONbored·added 2026-06-05·
Claude CodeCodexCursorClaude Desktop
HarnessClaude CodeCodexCursorClaude Desktop
Review first — review before installing

Open the source and read safety notes before installing.

Citation facts

Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.

Canonical URL
https://heyclau.de/entry/mcp/replicate-mcp-server
Source URLs
https://replicate.com/docs/reference/mcp, https://github.com/JSONbored/awesome-claude/blob/main/content/mcp/replicate-mcp-server.mdx
Safety notes
The server can invoke Replicate API capabilities through your account, so review prompts before running workflows that create predictions or consume credits., Keep code-mode or execution-oriented workflows separate from simple model search unless you intend to allow generated code execution.
Privacy notes
Model prompts, input URLs, generated outputs, and API account metadata can flow through Replicate and the MCP client context., Do not commit `REPLICATE_API_TOKEN` to a shared MCP config file.
Author
Replicate
Submitted by
JSONbored
Claim status
unclaimed
Last verified
2026-06-05

Decision playbook

Review trust signals before you adopt

Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.

Compare context
Selected

0

Current score

63

Baseline

—

Delta

No baseline selected

No major trust-signal divergence detected in the current selection.

Source and provenance checks

Needs review

Confirm ownership and provenance before trusting install instructions.

  • Source link availableRequired

    Open the canonical repository and verify ownership.

    Done

  • Source provenance statusRequired

    Marked as source-backed.

    Done

  • Metadata reviewed

    No reviewed flag detected in metadata.

    Pending

Safety and privacy checks

Complete

Validate risk disclosures before installation or API wiring.

  • Safety notes presentRequired

    Review the listed safety guidance before running commands.

    Done

  • Privacy notes presentRequired

    Review data handling notes before connecting accounts or secrets.

    Done

  • Trust level risk gateRequired

    Trust level does not block evaluation.

    Done

Package and install checks

Needs review

Check package metadata and artifact integrity signals.

  • Install payload available

    Install or copy payload is available for review.

    Done

  • Package verification flag

    No package verification flag provided.

    Pending

  • Checksum metadata

    No checksum provided for downloaded artifact.

    Pending

Compare-driven decision checks

Needs review

Use compare context to validate trade-offs before adoption.

  • Compare tray has multiple entries

    Add at least one more entry to compare trust differences.

    Pending

  • Baseline comparison available

    No baseline peer selected yet.

    Pending

  • Diverging trust signals identified

    No major trust-signal divergence found.

    Pending

Setup at a glance

CLI install

Copy-ready — paste the snippet to get started.

5 minutes

Install command

Provided

Config snippet

Provided

Copy snippet

Provided

Prerequisites

3 to clear

Platforms

4 listed

Install type

CLI install

Adoption plan

Balanced adoption plan

Current risk score 24/100. Use staged verification before broader rollout.

Risk 24

Pre-adoption checks

Validate source and review signals before any execution.

  • Confirm source provenanceRequired

    Source URL/provenance metadata is present.

    Done

  • Confirm metadata review state

    No review metadata found; increase manual validation.

    Pending

  • Verify install payload

    Install/config payload exists and can be inspected.

    Done

Security checks

Confirm safety, privacy, and package integrity signals.

  • Review safety notesRequired

    Safety notes are present.

    Done

  • Review privacy notesRequired

    Privacy notes are present.

    Done

  • Verify package integrity metadata

    No package verification/checksum metadata.

    Pending

Rollout

Adopt in controlled steps based on the selected plan.

  • Run in isolated sandbox firstRequired

    Use a constrained sandbox and observe behavior across multiple tasks.

    Pending

  • Roll out graduallyRequired

    Roll out to a small cohort before wider usage.

    Pending

  • Set monitoring and fallback

    Define rollback path and monitor errors after adoption.

    Pending

Evidence readiness

Evidence readiness matrix · balanced

Missing required evidence: Metadata review. Risk score 31.

Risk 31

Source provenance

Present

Source repository/provenance is listed.

Required in this preset

Metadata review

Missing

Review metadata is missing.

Required in this preset

Safety notes

Present

Safety notes are present.

Required in this preset

Privacy notes

Present

Privacy notes are present.

Optional in this preset

Package integrity

Missing

Package integrity metadata is missing.

Optional in this preset

Install payload

Present

Install payload is available.

Required in this preset

Required gaps: Metadata review

Decision timeline

Decision timeline · balanced

Blocking gaps: Check metadata review status. Risk 28.

Risk 28

triage

Confirm source provenanceRequired

Source/provenance metadata is available.

Done

triage

Check metadata review statusRequired

Review metadata is missing.

Pending

verify

Review safety notesRequired

Safety notes are available.

Done

verify

Review privacy notes

Privacy notes are available.

Done

verify

Validate package integrity metadata

Package integrity metadata is missing.

Pending

rollout

Verify install payload and commandsRequired

Install payload is available.

Done

Blockers: Check metadata review status

Prerequisite readiness

Prerequisite readiness

3 prerequisites to line up before setup. Have accounts and credentials ready first.

0/3 ready
Account & credentials1Install & runtime25 minutes

Safety & privacy surface

Safety & privacy surface

2 safety and 2 privacy notes across 3 risk areas. Review closely: credentials & tokens.

3 areas
  • SafetyExecution & processesThe server can invoke Replicate API capabilities through your account, so review prompts before running workflows that create predictions or consume credits.
  • SafetyGeneralKeep code-mode or execution-oriented workflows separate from simple model search unless you intend to allow generated code execution.
  • PrivacyGeneralModel prompts, input URLs, generated outputs, and API account metadata can flow through Replicate and the MCP client context.
  • PrivacyCredentials & tokensDo not commit `REPLICATE_API_TOKEN` to a shared MCP config file.

Safety notes

  • The server can invoke Replicate API capabilities through your account, so review prompts before running workflows that create predictions or consume credits.
  • Keep code-mode or execution-oriented workflows separate from simple model search unless you intend to allow generated code execution.

Privacy notes

  • Model prompts, input URLs, generated outputs, and API account metadata can flow through Replicate and the MCP client context.
  • Do not commit `REPLICATE_API_TOKEN` to a shared MCP config file.

Prerequisites

  • Node.js and npx available locally.
  • A Replicate API token stored outside version control.
  • Claude Desktop, Cursor, VS Code, or another MCP-compatible client.

Schema details

Install type
cli
Troubleshooting
No
Collection metadata
Estimated setup
5 minutes
Difficulty
beginner
Full copyable content
{
  "mcpServers": {
    "replicate": {
      "command": "npx",
      "args": ["-y", "replicate-mcp"],
      "env": {
        "REPLICATE_API_TOKEN": "your-token-here"
      }
    }
  }
}

About this resource

Content

Replicate MCP is Replicate's official MCP server for connecting AI clients to Replicate API tooling. The local server runs through npx -y replicate-mcp and uses a REPLICATE_API_TOKEN environment variable in client configuration. Replicate also publishes a hosted MCP surface for remote connection patterns.

Features

  • Local MCP server package launched with npx.
  • Works with Claude Desktop, Cursor, VS Code, and compatible MCP clients.
  • Lets agent workflows search Replicate and use Replicate API tooling from chat.
  • Supports token-backed account access through environment configuration.
  • Offers an advanced code-mode path for more complex SDK workflows.

Installation

Create a Replicate API token, then add the server to your MCP client config:

{
  "mcpServers": {
    "replicate": {
      "command": "npx",
      "args": ["-y", "replicate-mcp"],
      "env": {
        "REPLICATE_API_TOKEN": "your-token-here"
      }
    }
  }
}

Restart the client and ask it to search Replicate for a small model category to confirm the tool is connected.

Use Cases

  • Find candidate Replicate models for image, audio, video, or language workflows.
  • Draft API calls using current model metadata.
  • Compare model inputs before building a workflow.
  • Let a coding assistant scaffold Replicate SDK usage with account-aware context.

Safety and Privacy

Treat the API token like any other paid service credential. Keep it in local MCP settings, a keychain-backed client, or an environment variable, and avoid sharing workspace-level config that contains the token. Review generated prompts and code before creating predictions that consume credits.

Duplicate Check

Existing tool listings include Replicate-adjacent AI tooling, but no dedicated MCP entry for the official Replicate server was found in content/mcp.

References

#replicate#models#image-generation#api-tools#official

Source citations

Add this badge to your README

Show that Replicate MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/mcp/replicate-mcp-server.svg)](https://heyclau.de/entry/mcp/replicate-mcp-server)

How it compares

Replicate MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

1 trust signal differ across this comparison (Submitter).

Field
Replicate MCP Server

Official Replicate MCP server for using Replicate model search, API tooling, and optional code-mode workflows from Claude Desktop, VS Code, Cursor, and compatible MCP clients.

Open dossier
Microsoft logoMicrosoft Learn MCP Server

Official Microsoft Learn remote MCP server that gives AI agents real-time access to Microsoft documentation search, page fetch, and code sample search.

Open dossier
Tavily MCP Server for Claude

Official Tavily MCP server that gives Claude agent-optimized web search and page extraction, returning concise, source-cited results designed for LLM reasoning rather than raw search engine pages.

Open dossier
Brave Search logoBrave Search MCP Server

Official Brave Search MCP server for giving Claude web, local, place, image, video, news, LLM context, and summarizer search tools backed by the Brave Search API.

Open dossier
Next steps
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Trust
Review statusNot reviewedNot reviewedNot reviewedNot reviewed
Package trustPackage not verifiedPackage not verifiedPackage not verifiedPackage not verified
Source provenanceSource-backedSource-backedSource-backedSource-backed
SubmitterDiffersJSONboredJSONboredglorydavid03023oktofeesh1
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
Brand—Microsoft logoMicrosoft—Brave Search logoBrave Search
Categorymcpmcpmcpmcp
SourceSource-backedSource-backedSource-backedSource-backed
AuthorReplicateMicrosoftTavilyBrave Software
Added2026-06-052026-06-052026-06-032026-06-06
Platforms
Claude CodeCodexCursorClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Harness
Claude CodeCodexCursorClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Source repo————
Safety notes✓The server can invoke Replicate API capabilities through your account, so review prompts before running workflows that create predictions or consume credits. Keep code-mode or execution-oriented workflows separate from simple model search unless you intend to allow generated code execution.✓The server is documentation-focused, but retrieved docs can still influence generated commands; review commands before running them. Remote MCP availability and schema can change, so verify client compatibility before depending on it in automation.✓Makes outbound network requests to the Tavily API to run searches and fetch page content. Returned search results and extracted page text are untrusted web content; review it before acting on instructions or links it contains.✓Brave Search MCP uses BRAVE_API_KEY from the MCP client environment or command-line options. The server defaults to stdio transport in version 2.x and can also run an HTTP transport when explicitly configured. Tools can send web, news, image, video, local, place, and LLM-context queries to the Brave Search API. Local and place tools may use location strings, coordinates, postal codes, or optional location headers. Summarizer workflows depend on summary keys returned by web search and should be checked against cited source URLs. API usage may be metered or plan-limited, especially for Pro-only local search capabilities and extra snippets.
Privacy notes✓Model prompts, input URLs, generated outputs, and API account metadata can flow through Replicate and the MCP client context. Do not commit `REPLICATE_API_TOKEN` to a shared MCP config file.✓Prompts and queries sent to a remote MCP server can reveal product names, architecture details, or error messages. Avoid sending customer identifiers or private tenant data when documentation search is enough.✓Search queries and target URLs you provide are sent to the Tavily service to return results, so avoid embedding secrets in queries. The Tavily API key is a credential; store it as an environment variable and never commit it to source control.✓Search queries, location parameters, result filters, language settings, freshness windows, and optional headers may reveal user intent, location, research topics, or sensitive business context. BRAVE_API_KEY should stay out of prompts, issues, logs, screenshots, and committed files. Returned snippets, summaries, search results, local-business metadata, images, videos, and news items can include third-party copyrighted or sensitive content. HTTP transport should be bound and exposed carefully so the API key and search tools are not reachable by untrusted clients.
Prerequisites
  • Node.js and npx available locally.
  • A Replicate API token stored outside version control.
  • Claude Desktop, Cursor, VS Code, or another MCP-compatible client.
  • An MCP-compatible client that supports remote HTTP MCP servers.
  • Network access to learn.microsoft.com.
  • A Microsoft technology question where official Learn grounding is useful.
  • Node.js 18+ and npx available (verify with: npx --version)
  • A Tavily API key (create one at https://tavily.com)
  • Claude Code or Claude Desktop with MCP support
  • Internet access so the server can reach the Tavily API
  • Brave Search API account and API key.
  • Node.js and npm available in the MCP client runtime.
  • API plan review for web, local, extra snippets, summarizer, and LLM context usage.
  • Tool whitelist or blacklist if the client should expose only selected search tools.
Install
npx -y replicate-mcp
claude mcp add --transport http microsoft-learn https://learn.microsoft.com/api/mcp
claude mcp add tavily --env TAVILY_API_KEY=YOUR_KEY -- npx -y tavily-mcp@latest
npx -y @brave/brave-search-mcp-server --transport stdio
Config
{
  "mcpServers": {
    "replicate": {
      "command": "npx",
      "args": ["-y", "replicate-mcp"],
      "env": {
        "REPLICATE_API_TOKEN": "your-token-here"
      }
    }
  }
}
{
  "mcpServers": {
    "microsoft-learn": {
      "url": "https://learn.microsoft.com/api/mcp"
    }
  }
}
{
  "mcpServers": {
    "tavily": {
      "command": "npx",
      "args": [
        "-y",
        "tavily-mcp@latest"
      ],
      "env": {
        "TAVILY_API_KEY": "${TAVILY_API_KEY}"
      },
      "type": "stdio"
    }
  }
}
{
  "mcpServers": {
    "brave-search": {
      "command": "npx",
      "args": ["-y", "@brave/brave-search-mcp-server", "--transport", "stdio"],
      "env": {
        "BRAVE_API_KEY": "<your-brave-search-api-key>"
      }
    }
  }
}
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed
Open 4 picks in the interactive comparison tool

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.