{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"awesome-make","slug":"make","name":"Make","type":"mcp","url":"https://github.com/integromat/make-mcp-server","page_url":"https://unfragile.ai/make","categories":["mcp-servers","automation"],"tags":[],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"awesome-make__cap_0","uri":"capability://tool.use.integration.make.scenario.exposure.as.mcp.tools","name":"make scenario exposure as mcp tools","description":"Exposes Make.com automation scenarios as callable tools through the Model Context Protocol (MCP), enabling AI assistants to invoke pre-built workflows without direct API knowledge. The MCP server acts as a bridge that translates scenario definitions into tool schemas that LLMs can discover and invoke, handling authentication to Make's API and parameter mapping between the assistant's tool calls and Make's scenario execution format.","intents":["I want my AI assistant to trigger existing Make workflows without writing custom integrations","I need to expose my Make automations as discoverable tools in an MCP-compatible AI system","I want to let Claude or other LLMs execute my Make scenarios as part of a larger agentic workflow"],"best_for":["Teams using Make.com for workflow automation who want to integrate with AI assistants","Developers building AI agents that need to orchestrate existing Make scenarios","Non-technical users who have built Make workflows and want AI-driven execution"],"limitations":["Requires pre-existing Make scenarios — cannot create new scenarios from the MCP server","Tool discovery depends on Make API returning accurate scenario metadata; schema generation is limited to what Make exposes","No built-in retry logic or error recovery — failures in Make execution propagate directly to the LLM","Authentication is static per server instance — no per-user credential isolation"],"requires":["Make.com account with active scenarios","Make API credentials (API token or OAuth setup)","MCP-compatible AI assistant or framework (Claude, custom LLM agent, etc.)","Node.js runtime (inferred from GitHub repo structure)"],"input_types":["scenario parameters (strings, numbers, booleans, arrays)","structured JSON payloads matching scenario input schema"],"output_types":["scenario execution results (JSON)","execution status and metadata","error messages from Make API"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-make__cap_1","uri":"capability://tool.use.integration.dynamic.scenario.discovery.and.schema.generation","name":"dynamic scenario discovery and schema generation","description":"Automatically discovers all accessible Make scenarios from a user's Make account and generates MCP-compatible tool schemas by querying Make's API for scenario metadata, input/output definitions, and execution parameters. The server introspects scenario structure and converts it into JSON Schema format that LLMs can understand, eliminating manual tool registration and keeping schemas in sync with scenario changes.","intents":["I want my AI assistant to automatically see all my Make scenarios without manual configuration","I need tool schemas that stay synchronized when I update my Make workflows","I want to avoid hardcoding scenario IDs and parameters in my AI agent code"],"best_for":["Teams with many Make scenarios who want dynamic tool availability","Developers who frequently modify Make workflows and need schema updates reflected automatically","Organizations using MCP servers as a central integration point for multiple AI assistants"],"limitations":["Schema generation accuracy depends on Make API's metadata completeness — complex nested parameters may not translate perfectly to JSON Schema","Discovery latency: initial scenario enumeration and schema generation adds startup time proportional to scenario count","No caching of scenario metadata — each server restart re-queries Make API, creating potential rate-limit exposure","Cannot infer semantic meaning of parameters from Make API alone; parameter descriptions rely on user-provided scenario documentation"],"requires":["Make API credentials with read access to scenarios","Make.com account with at least one scenario defined","Network connectivity to Make's API endpoints"],"input_types":["Make API responses (scenario metadata, parameter definitions)"],"output_types":["JSON Schema tool definitions","MCP tool discovery response format","parameter type and constraint metadata"],"categories":["tool-use-integration","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-make__cap_2","uri":"capability://tool.use.integration.scenario.execution.with.parameter.mapping","name":"scenario execution with parameter mapping","description":"Translates LLM tool calls into Make scenario executions by mapping the assistant's structured parameters to Make's execution API format, handling type coercion, validation, and payload construction. The server receives tool invocations from the MCP client, validates parameters against the scenario's schema, constructs the appropriate Make API request, and returns execution results back to the LLM in a standardized format.","intents":["I want my AI assistant to execute a Make scenario with specific parameters determined by the LLM's reasoning","I need parameter validation before sending requests to Make to avoid failed executions","I want execution results formatted consistently so my AI agent can parse and act on them"],"best_for":["AI agents that need to execute Make workflows as part of multi-step reasoning chains","Teams building autonomous systems that orchestrate Make automations","Developers integrating Make into larger AI-driven business processes"],"limitations":["Parameter mapping is one-directional (LLM → Make) — complex bidirectional data transformations require custom logic","No built-in timeout handling — long-running Make scenarios may cause MCP request timeouts","Execution results are returned as-is from Make API; no post-processing or result normalization","No transaction support — if a scenario partially fails, there's no automatic rollback mechanism"],"requires":["Valid Make API credentials with scenario execution permissions","Scenario ID and parameter schema already discovered via dynamic discovery","Make API availability and responsiveness"],"input_types":["MCP tool call with parameters (JSON)","scenario ID and parameter definitions"],"output_types":["Make scenario execution response (JSON)","execution status (success/failure)","execution result data or error details"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-make__cap_3","uri":"capability://tool.use.integration.mcp.protocol.compliance.and.tool.discovery","name":"mcp protocol compliance and tool discovery","description":"Implements the Model Context Protocol (MCP) server specification, exposing Make scenarios as tools that MCP-compatible clients (Claude, custom agents, etc.) can discover and invoke. The server handles MCP's tool listing, tool calling, and result streaming protocols, translating between MCP's standardized tool interface and Make's scenario execution model.","intents":["I want my Make scenarios to work with any MCP-compatible AI assistant without custom adapters","I need my AI system to discover available Make tools through standard MCP mechanisms","I want to use Make automations in a multi-tool agent that also uses other MCP servers"],"best_for":["Developers building MCP-compatible AI agents and systems","Teams standardizing on MCP for tool integration across multiple services","Organizations using Claude or other LLMs that support MCP tool calling"],"limitations":["MCP protocol overhead adds latency compared to direct API calls","Tool discovery is limited to MCP's tool listing mechanism — no advanced filtering or search","Streaming results depend on MCP client support; not all clients may handle streaming execution results","MCP version compatibility: server must track MCP spec updates to remain compatible"],"requires":["MCP-compatible client or AI framework","MCP server runtime (Node.js or equivalent)","Understanding of MCP protocol and tool schema format"],"input_types":["MCP tool list requests","MCP tool call requests with parameters"],"output_types":["MCP tool definitions (JSON Schema)","MCP tool call results","MCP error responses"],"categories":["tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-make__cap_4","uri":"capability://tool.use.integration.authentication.and.credential.management","name":"authentication and credential management","description":"Manages Make API authentication by storing and using API credentials (tokens or OAuth) to authorize requests to Make's API on behalf of the user. The server handles credential initialization, token refresh if needed, and secure transmission of authentication headers to Make, ensuring that tool execution requests are properly authenticated without exposing credentials to the LLM or MCP client.","intents":["I want to securely authenticate my MCP server to Make without hardcoding credentials in code","I need my AI assistant to execute Make scenarios with proper authorization","I want to manage Make API credentials centrally for my MCP server"],"best_for":["Production deployments of Make MCP servers","Teams managing multiple Make accounts or scenarios","Developers building secure AI agent systems that need credential isolation"],"limitations":["Credentials are stored in server memory or configuration — no built-in encryption at rest","No per-user credential isolation — all requests use the same Make API credentials","Token refresh logic depends on Make API's authentication model; OAuth flows may require additional setup","Credentials are not isolated from the MCP client — a compromised client can access Make through the server"],"requires":["Make API credentials (API token or OAuth credentials)","Secure credential storage mechanism (environment variables, secrets manager, etc.)","Make API authentication endpoint availability"],"input_types":["API credentials (token string or OAuth parameters)"],"output_types":["authenticated API requests to Make","authorization headers"],"categories":["tool-use-integration","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-make__cap_5","uri":"capability://tool.use.integration.error.handling.and.execution.status.reporting","name":"error handling and execution status reporting","description":"Captures and reports errors from Make scenario executions, including API failures, parameter validation errors, and scenario execution failures, translating them into human-readable messages that the LLM can understand and act upon. The server distinguishes between different error types (client errors, server errors, timeout) and returns structured error responses that include context for debugging and recovery.","intents":["I want my AI assistant to understand why a Make scenario failed and potentially retry or take alternative actions","I need detailed error messages from Make execution failures to debug workflow issues","I want my agent to handle Make API errors gracefully without crashing"],"best_for":["Developers building resilient AI agents that need to handle failures gracefully","Teams debugging Make workflow issues through AI-driven execution","Systems that need to provide users with meaningful error context from failed automations"],"limitations":["Error messages are limited to what Make API returns — some errors may lack semantic detail","No automatic retry logic — the LLM must decide whether to retry based on error type","Error categorization depends on Make API's error response format; inconsistencies may require custom parsing","Timeout errors may not distinguish between slow execution and actual failures"],"requires":["Make API error response format documentation","Error handling logic in the MCP server"],"input_types":["Make API error responses","HTTP status codes from Make API"],"output_types":["structured error messages (JSON)","error type classification","error context and debugging information"],"categories":["tool-use-integration","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":26,"verified":false,"data_access_risk":"high","permissions":["Make.com account with active scenarios","Make API credentials (API token or OAuth setup)","MCP-compatible AI assistant or framework (Claude, custom LLM agent, etc.)","Node.js runtime (inferred from GitHub repo structure)","Make API credentials with read access to scenarios","Make.com account with at least one scenario defined","Network connectivity to Make's API endpoints","Valid Make API credentials with scenario execution permissions","Scenario ID and parameter schema already discovered via dynamic discovery","Make API availability and responsiveness"],"failure_modes":["Requires pre-existing Make scenarios — cannot create new scenarios from the MCP server","Tool discovery depends on Make API returning accurate scenario metadata; schema generation is limited to what Make exposes","No built-in retry logic or error recovery — failures in Make execution propagate directly to the LLM","Authentication is static per server instance — no per-user credential isolation","Schema generation accuracy depends on Make API's metadata completeness — complex nested parameters may not translate perfectly to JSON Schema","Discovery latency: initial scenario enumeration and schema generation adds startup time proportional to scenario count","No caching of scenario metadata — each server restart re-queries Make API, creating potential rate-limit exposure","Cannot infer semantic meaning of parameters from Make API alone; parameter descriptions rely on user-provided scenario documentation","Parameter mapping is one-directional (LLM → Make) — complex bidirectional data transformations require custom logic","No built-in timeout handling — long-running Make scenarios may cause MCP request timeouts","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.05,"quality":0.22,"ecosystem":0.49999999999999994,"match_graph":0.25,"freshness":0.52,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.15,"match_graph":0.23,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-06-17T09:51:03.578Z","last_scraped_at":"2026-05-03T14:00:15.503Z","last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=make","compare_url":"https://unfragile.ai/compare?artifact=make"}},"signature":"eH4HkWxqICpAoUMmbIsgaQ2HaK+GKxrI88KE//RJrRraNQKGtl+AXkeZjzEshuIxOf0Kv30e3FuKp1VS49ewDw==","signedAt":"2026-06-21T04:45:29.249Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/make","artifact":"https://unfragile.ai/make","verify":"https://unfragile.ai/api/v1/verify?slug=make","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}