Replicate MCP Server
Provides authenticated access to Replicate through PipMCP, enabling model schema inspection, prediction creation with approval/policy controls, and retrieval of prediction status by ID.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Replicate MCP server
Use Replicate from Claude Code, Codex, Grok Build and MCP clients through PipMCP. One PipMCP API key connects this package to private execution.
Activate with PipMCP · Integration directory
Build something useful
Inspect the chosen model schema, approve prediction creation, then use the returned prediction ID to read status. Do not infer model success from the request transport result.
The package is an authenticated client: discovery, schemas, policy decisions and execution come from PipMCP. Provider implementation remains on the server.
Related MCP server: Replicate Universal MCP Server
Quick start
Requires Node.js 22+. Clone this repository, then:
npm ci --ignore-scripts
npm test
npm start
# After configuring your provider in PipMCP and setting PIPMCP_API_KEY:
npm start -- --live
# Launch the stdio MCP bridge:
npm run serverCreate a PipMCP API key with explicit connectors:read and connectors:call scopes. Set PIPMCP_API_KEY in the calling process environment. Provider credentials are configured in PipMCP. Multiple accounts require explicit PIPMCP_INTEGRATION_ID and PIPMCP_CONNECTION_ID from discovery. Existing keys do not gain scopes automatically.
Built for coding agents
Install this repository's skill into your project:
node lib/cli.mjs agents install --client codex --scope project --project /path/to/project
# Use claude or grok for those clients.Connect AI agents to Replicate using one PipMCP API key and actual hosted tool discovery. Native AGENTS.md, CLAUDE.md and project skills support the current coding session. No additional AI model key is required. capabilities.json describes the package; llms.txt indexes its instructions.
Inspect actual tools before calling
import {PipMCPGatewayClient} from './lib/index.mjs';
const client = new PipMCPGatewayClient(); // PIPMCP_API_KEY
const inventory = await client.getTools("replicate");
console.log(inventory.data.tools);
// Select a real tool and validate your arguments against its returned schema.
// client.callTool(provider, actualToolName, reviewedArguments, {idempotencyKey});PipMCP enforces workspace, role, connection, policy/approval and usage controls. Preserve the original idempotency key when retrieving/resuming a receipt. Pending and confirmation_required are not completed provider results; uncertain writes are held for reconciliation. The bridge never auto-approves a hosted action.
Version 1 migration
This release uses the authenticated PipMCP gateway for real discovery/execution. Upgrade your MCP launch command and configure PIPMCP_API_KEY before reconnecting. Historical local runtimes remain available under their original MIT license in Git history.
Evidence and support
Transport, package and agent fixtures are tested. Authentication/provider access must be checked in your own configured workspace; synthetic fixtures do not establish live provider execution. Do not include credentials or customer records in public issues. MIT covers this public client.
Provider setup reference
Official provider documentation. Credentials are entered in PipMCP; this package does not accept or store provider secrets.
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Pay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.
Remote MCP for RunComfy: ComfyUI deployments, hosted models, LoRA training. 31 tools.
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceEnables users to access and manage Replicate's AI models and predictions via the Model Context Protocol, offering tools for creating, canceling, and retrieving model predictions and parameters.1,969 npm94MIT
- AlicenseNot gradedqualityDmaintenanceProvides a standardized interface for interacting with Replicate's tools and services through a unified API, enabling AI model usage via MCP.111 PyPIMIT
- AlicenseNot gradedqualityBmaintenanceIt enables AI coding agents to authenticate through PipMCP, discover hosted tools, validate arguments against returned schemas, and invoke approved provider actions using a single API key.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents and MCP clients to discover and call governed Hugging Face tools through one PipMCP API key, including inspecting model branches, tags, revisions, and dataset references before execution.MIT