# Celigo MCP MCP Server > **Celigo MCP MCP Server** is a hosted, multitenant Model Context Protocol (MCP) server run by **MewCP** (https://mewcp.com), giving AI agents managed access to Celigo MCP. > > MewCP takes care of all MCP infrastructure for you — credential storage, OAuth flows, > token refresh, and production-grade auto-scaling — so your AI agents can connect to > third-party services and run freely without you managing any MCP server yourself. > > Server page: https://mewcp.com/mcp/celigo-mcp > MewCP docs: https://docs.mewcp.com > Full catalog: https://mewcp.com/llms.txt --- ## About Celigo's integrator.io connects business applications through hundreds of prebuilt connectors and automated integration flows. Build, deploy, and manage workflows across ERP, CRM, e-commerce, and other business systems; inspect execution logs, troubleshoot failed runs, manage API connections, monitor jobs, and control automation environments with built-in governance. --- ## Details - Server ID: `celigo-mcp` - Version: 0.12.0 - Tools: 61 - Authentication: OAuth, managed by MewCP - Transport: http --- ## Access The gateway URL below serves your **entire MewCP toolset**, not this server on its own. Pasting a config snippet is not enough — Celigo MCP has to be in the toolset first. In order: 1. Add Celigo MCP to your toolset at https://mewcp.com/mcp/celigo-mcp 2. Connect your Celigo MCP account (OAuth); MewCP stores the credential and attaches it to each call 3. Copy your MewCP API key from the dashboard (Developer) 4. Configure your client with the snippet for it below Once connected, an agent does **not** see this server's tools as top-level tools. It sees four meta-tools and reaches everything through them: - `search(query)` — find tools by keyword across the toolset - `get_schema(tools)` — full description and arguments for the tools you picked - `list_accounts(provider)` — only when one app has several connected accounts - `call_tool(server_maskedId, tool_name, args)` — execute So the list below is what `search` can return for this server, not a set of callable tool names on their own. --- ## Tools (61) Descriptions are truncated to 160 characters; call `get_schema` for the full text and the argument schema. Where a tool is annotated, its type is shown — treat `destructive` as irreversible. - `list_exports` _(read)_ — Data source steps (page generators) that fetch records from external systems. Each export is tied to a connection and defines what data to pull. adaptorType… - `upsert_export` _(destructive)_ — Create (omit `_id`; POST) or update (set `_id`; PUT) a export. Data source steps (page generators) that fetch records from external systems. Each export is… - `list_imports` _(read)_ — Data destination steps (page processors) that write records to external systems. Each import is tied to a connection and defines how to push data. adaptorType… - `upsert_import` _(destructive)_ — Create (omit `_id`; POST) or update (set `_id`; PUT) a import. Data destination steps (page processors) that write records to external systems. Each import is… - `list_flows` _(read)_ — Pipelines that move data from source (exports) to destination (imports). A flow contains pageGenerators[] (exports) and pageProcessors[] (imports/lookups),… - `upsert_flow` _(destructive)_ — Create (omit `_id`; POST) or update (set `_id`; PUT) a flow. Pipelines that move data from source (exports) to destination (imports). A flow contains… - `run_flow` _(destructive)_ — Run a flow — queues an on-demand execution and returns `_jobId`. Use `list_flow_runs` with `_id` set to that `_jobId` to poll status and inspect results… - `list_flow_errors` _(read)_ — List open errors for flow steps. Four modes: 1. With `_id` + `_stepId`: errors for a specific step (body-paginated, returns `{ errors, nextCursor?, hasMore }`)… - `get_flow_error_retry_data` _(read)_ — Get the stored retry-data snapshot for one error (`retryDataKey` from `list_flow_errors`). Returns the envelope the runtime captured at failure (`data`,… - `update_flow_error_retry_data` _(destructive)_ — Full-replace of the stored retry-data snapshot for one error. Body is the complete envelope from `get_flow_error_retry_data` (mutate `data` as needed). Does… - `list_execution_logs` _(read)_ — Flow run execution logs (debug/trace). Requires `_id` (flow) and `_jobId` (parent job from `run_flow` or `list_flow_runs`). Flow must have debug logging armed… - `patch_flow` _(destructive)_ — Partially update a flow via JSON Patch (safer than `upsert_flow` PUT for one-field changes). Common disable/enable toggle: `body: [{ "op": "replace", "path":… - `list_connections` _(read)_ — Credentials and configuration for external systems. Each connection holds auth details (API keys, OAuth tokens, etc.) and is shared across exports and imports.… - `upsert_connection` _(destructive)_ — Create (omit `_id`; POST) or update (set `_id`; PUT) a connection. Credentials and configuration for external systems. PUT is a full-document replace, not a… - `list_integrations` _(read)_ — Top-level containers that group flows, connections, and resources into a logical project. Every flow belongs to an integration. Use list_integrations to see… - `upsert_integration` _(destructive)_ — Create (omit `_id`; POST) or update (set `_id`; PUT) a integration. Top-level containers that group flows, connections, and resources into a logical project.… - `list_scripts` _(read)_ — JavaScript hook scripts for data transformation and custom logic. Scripts are referenced by exports/imports via the hooks object (preSavePage, preMap, postMap,… - `upsert_script` _(destructive)_ — Create (omit `_id`; POST) or update (set `_id`; PUT) a script. JavaScript hook scripts for data transformation and custom logic. Scripts are referenced by… - `list_ai_agents` _(read)_ — Celigo AI Agents (import steps with adaptorType AiAgentImport). Configure via `aiAgent` — provider (openai/gemini), model, system instructions, tools (Celigo… - `upsert_ai_agent` _(destructive)_ — Create (omit `_id`; POST) or update (set `_id`; PUT) a ai agent. Celigo AI Agents (import steps with adaptorType AiAgentImport). Configure via `aiAgent` —… - `list_guardrails` _(read)_ — Guardrail resources — safety/compliance checks (PII, moderation, AI eval) implemented as import steps (`adaptorType=GuardrailImport`); they also appear in… - `upsert_guardrail` _(destructive)_ — Create (omit `_id`; POST) or update (set `_id`; PUT) a guardrail. Guardrail resources — safety/compliance checks (PII, moderation, AI eval) implemented as… - `list_apis` _(read)_ — Celigo API resources — custom HTTP endpoints you publish so external systems can invoke a flow/tool synchronously over REST. Dual-purpose tool: omit `_id` to… - `upsert_api` _(destructive)_ — Create (omit `_id`; POST) or update (set `_id`; PUT) a api. Celigo API resources — custom HTTP endpoints you publish so external systems can invoke a flow/tool… - `list_environments` _(read)_ — Account environments (sandbox/staging). Feature-gated: accounts without multi-environment return an empty list + `_warning` (not an error). See each… - `list_iclients` _(read)_ — iClient resources — shared OAuth2 app registrations (client id/secret, token URI) that connections reference to authenticate. On PUT, resend… - `upsert_iclient` _(destructive)_ — Create (omit `_id`; POST) or update (set `_id`; PUT) a iclient. iClient resources — shared OAuth2 app registrations (client id/secret, token URI) that… - `list_lookup_caches` _(read)_ — In-memory key-value stores for lookups and deduplication. Use `list_lookup_caches` (Phase 1) to find a cache `_id`; `upsert_lookup_cache` (Phase 2) creates the… - `upsert_lookup_cache` _(destructive)_ — Create (omit `_id`; POST) or update (set `_id`; PUT) a lookup cache. In-memory key-value stores for lookups and deduplication. Use `list_lookup_caches` (Phase… - `list_lookup_cache_data` _(read)_ — Read entries from an existing lookup cache. Requires cache `_id` from `list_lookup_caches`. Omit filters for the first page (~1000 entries); pass `key` (single… - `upsert_lookup_cache_data` _(destructive)_ — Load or replace entries in an existing lookup cache. Body: `{ data: [{ key, value }, ...] }`. Automatically splits into batches of 1000 entries (API limit per… - `delete_lookup_cache_data` _(destructive)_ — Remove entries from a lookup cache. Pass `key` or `keys` to delete specific entries (`DELETE .../data` with `{ keys }`). To purge **every** entry, set `all:… - `list_tools` _(read)_ — Celigo Tool resources — reusable integration building blocks (lookups/imports/transforms behind an input/output contract) stored in your account. NOT the MCP… - `upsert_tool` _(destructive)_ — Create (omit `_id`; POST) or update (set `_id`; PUT) a tool. Celigo Tool resources — reusable integration building blocks (lookups/imports/transforms behind an… - `list_mcp_servers` _(read)_ — Celigo-hosted MCP server resources your account publishes to external AI agents — not this server. Dual-purpose tool: omit `_id` to list the collection… - `upsert_mcp_server` _(destructive)_ — Create (omit `_id`; POST) or update (set `_id`; PUT) a mcp server. Celigo-hosted MCP server resources your account publishes to external AI agents — not this… - `list_flow_runs` _(read)_ — Dual-purpose job inspector. **Get job family** (recommended): Set `_id` to a parent flow job id to fetch the complete run — returns the parent job plus… - `list_current_jobs` _(read)_ — List currently in-progress jobs via `POST /v1/jobs/current`. Returns only queued, running, or canceling jobs as `{ items, hasMore, nextCursor? }`; terminal… - `cancel_flow_run` _(destructive)_ — Cancel a queued/running flow run by job `_id` (from `run_flow`'s `_jobId` or `list_flow_runs`). Cancelling a parent flow job cancels its child export/import… - `list_tags` _(read)_ — List all error tags in the account. Use each entry's `tagId` short code (not Mongo `_id`) in `triage_flow_errors` (`tagIds` on action `tag`). Calls the Celigo… - `list_audit_log_entries` _(read)_ — List audit log entries (newest first). Returns a page `{ items, hasMore, paginationNote }` where each item includes `resourceType`, `_resourceId`,… - `list_edi_profiles` _(read)_ — EDI interchange envelope profiles for B2B Manager (X12 ISA/GS and EDIFACT UNB control fields). Define sender/receiver IDs, qualifiers, and standards versions… - `upsert_edi_profile` _(destructive)_ — Create (omit `_id`; POST) or update (set `_id`; PUT) a edi profile. EDI interchange envelope profiles for B2B Manager (X12 ISA/GS and EDIFACT UNB control… - `list_file_definitions` _(read)_ — File structure and parsing rules for structured files (CSV, fixed-width, EDI X12, EDI EDIFACT). Exports and imports reference a file definition to control how… - `upsert_file_definition` _(destructive)_ — Create (omit `_id`; POST) or update (set `_id`; PUT) a file definition. File structure and parsing rules for structured files (CSV, fixed-width, EDI X12, EDI… - `list_edi_transactions` _(read)_ — Query the B2B Manager EDI transaction log. Dual-purpose: omit `_id` to list (POST /v1/ediTransactions/query); set `_id` to return one transaction (scans the… - `update_edi_fa_status` _(destructive)_ — Update functional-acknowledgement status on a batch of EDI transactions (PATCH /v1/ediTransactions). Body: `{ "fileType": "X12"|"EDIFACT", "ediTransactions":… - `list_marketplace` _(read)_ — Browse the published marketplace catalog or preview one template's full blueprint. **List** (omit `_id`): `POST /v1/published/combined` sorted by `numInstalls`… - `list_storage_items` _(read)_ — Browse or search Celigo Storage (managed files & folders). Three modes: **List** (default): returns the direct children of one folder plus a `breadcrumb` of… - `restore_storage_item` _(write)_ — Restore a soft-deleted Celigo Storage item from the recycle bin back to its original location. Find recycle-bin ids with `list_storage_items` (`deleted:… - `get_storage_file_download_url` _(read)_ — Get a short-lived presigned URL for one Celigo Storage file's content. Returns `{ downloadUrl, expiresIn }` (seconds the URL stays valid). Fetch the bytes with… - `cancel_storage_upload` _(destructive)_ — Abort an abandoned pending multipart **create** upload, discard uploaded parts, and release its reserved quota. Do not call this for… - `install_template` _(write)_ — Install a published marketplace template, creating a new integration (POST /v1/integrations/template/{_id}). **Requires `connectionMap`** in `body`: maps each… - `delete_resource` _(destructive)_ — Delete a resource by `_id`. Pass `resourceType` to select the resource family (allowed values: exports, imports, flows, connections, integrations, scripts,… - `get_schema` _(read)_ — **Essential companion to upsert_* tools.** Returns exact field structures, required properties, enum values, and array vs object distinctions. Call BEFORE… - `search_docs` _(read)_ — Search the Celigo Knowledge Base and get AI-generated answers about integrator.io. Returns `{ answer, sources[], thread_id }`. Use for how-to/product… - `list_users` _(read)_ — List every user in the current account: the account **owner** (prepended, `accessLevel: "owner"`) plus all invited/shared users from the account-share list… - `manage_user` _(destructive)_ — Perform one account-user management action. **Admin-only** (account owner or administrator); `update_permissions` and `disable` carry blast radius — confirm… - `upsert_storage_item` _(destructive)_ — Create or update a Celigo Storage item (file or folder). Omit `_id` to create; pass `_id` (from `list_storage_items`) to update. The operation is chosen from… - `triage_flow_errors` _(destructive)_ — Perform one flow-step error action. Requires `_id` (flow), `_stepId` (export/import id), and `action`. Pass `body` for targeted ops, or `resolveAll` /… - `submit_feedback` _(write)_ — Submit product feedback about the Celigo CLI or platform MCP experience (`POST /v1/feedbacks`). Use when the user (or you) wants to report a bug, confusion,… --- ## Connect Gateway URL: https://gateway.mewcp.com/personal/mcp Every request carries one header: Authorization: Bearer Replace `API_KEY` with your own key from the dashboard (Developer). ## Apps ### Claude Desktop Mac & Windows app - macOS: `~/Library/Application Support/Claude/claude_desktop_config.json` - Windows: `%APPDATA%\Claude\claude_desktop_config.json` ```json { "mcpServers": { "mewcp": { "command": "npx", "args": [ "-y", "mcp-remote@latest", "https://gateway.mewcp.com/personal/mcp", "--header", "Authorization:${AUTH_HEADER}" ], "env": { "AUTH_HEADER": "Bearer API_KEY" } } } } ``` Already have an "mcpServers" section in your config? Just add the server entry inside it. 1. Open Claude Desktop → Settings → Developer → "Edit Config" 2. Paste the snippet inside the outer { } of the config file (merge with your existing "mcpServers" section if you have one) 3. Save the file, then quit Claude Desktop completely and reopen it 4. Start a new conversation — your tool will be available ### VS Code Copilot / Cline - Command Palette → "MCP: Open User Configuration" (opens mcp.json). For one project only, use .vscode/mcp.json instead. ```json { "mcp.servers": { "mewcp": { "type": "http", "url": "https://gateway.mewcp.com/personal/mcp", "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Already have a "servers" section in your mcp.json? Just add the server entry inside it. 1. Open VS Code → Command Palette (Cmd+Shift+P / Ctrl+Shift+P) 2. Run "MCP: Open User Configuration" to open your mcp.json 3. Paste the snippet and save 4. Start the server when prompted (or from the MCP servers view) and use it in Copilot Chat ### Cursor AI-first editor - macOS: `~/.cursor/mcp.json` - Windows: `%USERPROFILE%\.cursor\mcp.json` ```json { "mcpServers": { "mewcp": { "url": "https://gateway.mewcp.com/personal/mcp", "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Already have an "mcpServers" section in your mcp.json? Just add the server entry inside it. 1. Open Cursor → Settings → Cursor Settings → MCP 2. Click "Add new global MCP server" 3. Paste the snippet and save 4. Restart Cursor ### Codex OpenAI's CLI agent - Add the snippet to your Codex MCP config or your standard MCP config file for the CLI tool you use. ```json { "mcpServers": { "mewcp": { "type": "http", "url": "https://gateway.mewcp.com/personal/mcp", "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Codex generally reads a standard MCP server block, so you can add this alongside your other configured servers. 1. Open your Codex MCP config or project-level config file 2. Paste the MewCP server block inside the config JSON/TOML structure your tool expects 3. Save the file and restart Codex 4. Verify the tool is available inside a fresh session ### Claude Code Anthropic's CLI agent - ~/.claude.json (user scope) or .mcp.json in your project root — create it if it doesn't exist. Or skip the file and use the CLI command below. ```json { "mcpServers": { "mewcp": { "type": "http", "url": "https://gateway.mewcp.com/personal/mcp", "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Already have an "mcpServers" section in your config? Just add the server entry inside it. 1. Open ~/.claude.json (or .mcp.json in your project root) in a text editor 2. Paste the snippet inside the outer { } (merge with your existing "mcpServers" section if you have one) 3. Save the file and start (or restart) Claude Code 4. Or skip the file entirely and run the CLI command below instead ### OpenCode Open-source terminal agent - ~/.config/opencode/opencode.json (global) or opencode.json in your project root — create it if it doesn't exist. ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "mewcp": { "type": "remote", "url": "https://gateway.mewcp.com/personal/mcp", "enabled": true, "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Already have an "mcp" section in your opencode.json? Just add the server entry inside it. 1. Open ~/.config/opencode/opencode.json (or opencode.json in your project root) in a text editor 2. Paste the snippet inside the outer { } (merge with your existing "mcp" section if you have one) 3. Save the file and start (or restart) OpenCode ### OpenClaw Self-hosted agent gateway - ~/.openclaw/openclaw.json — create it if it doesn't exist. ```json { "mcp": { "servers": { "mewcp": { "transport": "streamable-http", "url": "https://gateway.mewcp.com/personal/mcp", "enabled": true, "headers": { "Authorization": "Bearer API_KEY" } } } } } ``` Already have an "mcp" section in your openclaw.json? Just add the server entry inside "servers". 1. Open ~/.openclaw/openclaw.json in a text editor 2. Paste the snippet inside the outer { } (merge with your existing "mcp" section if you have one) 3. Save the file and restart OpenClaw ### Antigravity Google's agentic IDE - ~/.gemini/config/mcp_config.json (global) or .agents/mcp_config.json (workspace-local) — create it if it doesn't exist. ```json { "mcpServers": { "mewcp": { "serverUrl": "https://gateway.mewcp.com/personal/mcp", "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Already have an "mcpServers" section in your config? Just add the server entry inside it. Remote servers must use the "serverUrl" field — the legacy "url"/"httpUrl" fields aren't supported. 1. In the editor's agent side panel, click "…" → "MCP Servers" → "Manage MCP Servers" → "View raw config" (Antigravity CLI: type /mcp instead to open the Interactive MCP Manager) 2. Paste the snippet inside the outer { } (merge with your existing "mcpServers" section if you have one) 3. Save the file — the server connects automatically ### Hermes Nous Research's CLI agent - config.yaml in your Hermes config directory (~/.hermes) — add this under a top-level "mcp_servers:" key. ```yaml mcp_servers: mewcp: url: "https://gateway.mewcp.com/personal/mcp" headers: Authorization: "Bearer API_KEY" ``` Already have an "mcp_servers" section in your config.yaml? Just add the server entry inside it. 1. Open config.yaml in your Hermes config directory 2. Paste the snippet under the top-level "mcp_servers:" key (merge with existing entries if you have any) 3. Save the file, then run /reload-mcp in Hermes (or start a fresh session) 4. Ask Hermes "Tell me which MCP-backed tools are available right now" to confirm it connected ### DeepSeek Harness DeepSeek's agent harness - cordis.yml in your DSH project — or the patch file you mount plugins from. ```yaml - id: mcp-mewcp name: '@deepseek-ai/dsh-mcp-client' config: serverName: mewcp transport: streamable-http url: https://gateway.mewcp.com/personal/mcp headers: Authorization: "Bearer API_KEY" ``` One plugin instance = one MCP server. Add this entry to your plugin list; don't nest it inside another entry. 1. Open cordis.yml (or your patch file) in your DSH project 2. Paste the entry into your plugin list, keeping the leading dash and indentation 3. Restart DSH (or let HMR reload) — tools register as mcp__mewcp__ 4. Verify with: dsh web --dump-config | grep -A3 mcp ## SDKs ### Python fastmcp client ```python import asyncio from fastmcp import Client from fastmcp.client.transports import StreamableHttpTransport SERVER_URL = "https://gateway.mewcp.com/personal/mcp" API_KEY = "API_KEY" transport = StreamableHttpTransport( url=SERVER_URL, headers={ "Authorization": f"Bearer {API_KEY}", } ) async def main(): client = Client(transport) async with client: tools = await client.list_tools() print(tools) asyncio.run(main()) ``` 1. Install fastmcp: pip install fastmcp 2. Copy the snippet into your project 3. Replace API_KEY with your key from the dashboard 4. Run your script ### TypeScript MCP SDK ```typescript import { Client } from "@modelcontextprotocol/sdk/client/index.js"; import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js"; const SERVER_URL = "https://gateway.mewcp.com/personal/mcp"; const API_KEY = "API_KEY"; const transport = new StreamableHTTPClientTransport(new URL(SERVER_URL), { requestInit: { headers: { Authorization: `Bearer ${API_KEY}`, }, }, }); const client = new Client({ name: "mewcp-client", version: "1.0.0" }); await client.connect(transport); const tools = await client.listTools(); console.log(tools.tools.map((t) => t.name)); ``` 1. Install: npm install @modelcontextprotocol/sdk 2. Copy the snippet into your project 3. Replace API_KEY with your key from the dashboard 4. Run with Node 18+ as an ES module (e.g. npx tsx script.ts)