The Apideck MCP server provides a dynamic gateway to 330+ API tools across 10 unified APIs, connecting to 200+ third-party services (Accounting, CRM, HRIS, File Storage, ATS, Issue Tracking, Ecommerce, Webhooks, Vault, Proxy) through a single integration.
Core meta-tools:
list_tools – Browse all 330+ tools or filter by search terms/scopes for token-efficient discovery.
describe_tool_input – Retrieve the full JSON Schema for any tool to understand required/optional parameters.
execute_tool – Run any endpoint tool (e.g., list invoices, create CRM contacts, upload files, fetch employees, manage webhooks).
list_scopes – View scope categories (read, write, destructive) for filtering tools by operation type.
Additional capabilities:
Workflow tools – Orchestrate multi-step tasks (e.g., month-end close checks).
Binary content handling – Images and audio from File Storage returned as native MCP content blocks.
Multiple modes – Operate in dynamic (progressive discovery), static (all tools exposed), or code (programmatic via apideck_search/apideck_run) modes.
Automatic retries – Built-in request retry logic for improved reliability.
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent to 200+ connectors — accounting systems, HRIS platforms, CRM, file storage, and more — through one integration.
Recommended — prebuilt bundle:
Drag and drop the prebuilt mcp-server.mcpb onto Claude Desktop. Claude reads manifest.json to prompt for credentials and spawn the server — no manual config needed.
Learn more aboutDesktop Extensions.
Local stdio (npx) alternative:
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"apideck": {
"command": "npx",
"args": ["-y", "@apideck/mcp", "start"],
"env": {
"APIDECK_API_KEY": "YOUR_API_KEY",
"APIDECK_CONSUMER_ID": "YOUR_CONSUMER_ID",
"APIDECK_APP_ID": "YOUR_APP_ID"
}
}
}
}Restart Claude Desktop after saving. Pin a specific version by replacing @apideck/mcp with @apideck/mcp@0.1.15.
Set credentials in your shell:
export APIDECK_API_KEY="..."
export APIDECK_CONSUMER_ID="..."
export APIDECK_APP_ID="..."Hosted (recommended):
claude mcp add --transport http apideck https://mcp.apideck.dev/mcp \
--header "Authorization: Bearer $APIDECK_API_KEY" \
--header "x-apideck-consumer-id: $APIDECK_CONSUMER_ID" \
--header "x-apideck-app-id: $APIDECK_APP_ID"Local stdio (npx):
claude mcp add apideck \
-e APIDECK_API_KEY="$APIDECK_API_KEY" \
-e APIDECK_CONSUMER_ID="$APIDECK_CONSUMER_ID" \
-e APIDECK_APP_ID="$APIDECK_APP_ID" \
-- npx -y @apideck/mcp startThe start command reads credentials from environment variables only — it does not accept --api-key / --consumer-id / --app-id flags.
Settings → Cascade → Manage MCPs → View raw config, then paste:
{
"mcpServers": {
"apideck": {
"url": "https://mcp.apideck.dev/mcp",
"headers": {
"x-apideck-api-key": "YOUR_API_KEY",
"x-apideck-consumer-id": "YOUR_CONSUMER_ID",
"x-apideck-app-id": "YOUR_APP_ID"
}
}
}
}{
"mcpServers": {
"apideck": {
"url": "https://mcp.apideck.dev/mcp",
"headers": {
"x-apideck-api-key": "YOUR_API_KEY",
"x-apideck-consumer-id": "YOUR_CONSUMER_ID",
"x-apideck-app-id": "YOUR_APP_ID"
}
}
}
}Related MCP server: NetSuite MCP Server by CData
Apideck ships a Claude plugin bundle (.mcpb — Anthropic's Model Context Protocol Bundle format). Drop it into Claude Desktop and you get the full server (330 endpoint tools + 4 workflow tools) with API key / consumer ID / app ID prompted via the standard plugin UI.
pnpm mcpb:build # → dist/mcp-server.mcpb (~590 KB)The bundle is built locally; CI publication to GitHub Releases is deferred. Open the .mcpb with Claude Desktop's plugin installer; Claude Desktop reads manifest.json to wire credentials and spawn the server.
330 tools across 10 unified APIs:
API | Tools | Coverage |
Accounting | 143 | Invoices, bills, payments, suppliers, customers, journal entries, ledger accounts, purchase orders, tax rates, P&L, balance sheet, and more |
CRM | 50 | Companies, contacts, leads, opportunities, pipelines, notes, activities, users |
File Storage | 32 | Files, folders, drives, shared links, upload sessions |
HRIS | 25 | Employees, companies, departments, payrolls, time-off requests |
Vault | 23 | Connections, consumers, sessions, custom mappings, logs |
ATS | 15 | Applicants, applications, jobs |
Issue Tracking | 15 | Collections, tickets, users, tags, comments |
Connector | 8 | APIs, connectors, resources, coverage metadata |
Ecommerce | 7 | Customers, orders, products, stores |
Webhook | 6 | Webhook subscriptions, logs |
Proxy | 6 | GET, POST, PUT, PATCH, DELETE, OPTIONS |
Intent-grouped workflows orchestrate multiple calls behind a single MCP tool — saving agents the round-trips and field-plumbing they routinely get wrong.
Tool | What it does | Calls |
| Fans out aged-creditors, aged-debtors, balance-sheet, and P&L in parallel. Returns a partial result when some reports aren't supported by the connector. | 4 |
The server is live at:
https://mcp.apideck.dev/mcpPass credentials via headers:
Header | Description |
| Your Apideck API key |
| The end-user / customer ID in your app (optional — see below) |
| Your Apideck application ID |
The consumer ID is optional at connect time. Leave APIDECK_CONSUMER_ID /
x-apideck-consumer-id unset to start the server unscoped, then supply or
override the consumer per call by passing a consumer_id argument to any tool:
execute_tool({ name: "crm-contacts-all", input: { consumer_id: "acme-inc" } })Precedence: the per-call consumer_id argument wins over the
APIDECK_CONSUMER_ID env var / x-apideck-consumer-id header.
Unscoped calls work for application-scoped endpoints that don't need a
consumer — e.g. webhook logs (webhook-event-logs-all) and
vault-connections-all.
Consumer-scoped endpoints called without a consumer return Apideck's
"consumer required" error, so set consumer_id (or the env/header) for those.
Mode | Tools exposed | Initial tokens | Best for |
| 4 meta-tools | ~1,300 | General-purpose agents, token-sensitive contexts |
| All 330 tools | ~35–55K | Focused agents doing a specific API |
|
| ~600 | Agents that call endpoints programmatically via JS |
Agents discover tools progressively — ~85% fewer tokens than loading all 330 schemas upfront:
list_tools({})
→ { total: 330, domains: [{ name: "accounting", count: 143 }, ...],
hint: "Call list_tools(domain=X) or list_tools(search_terms=[...])" }
list_tools({"search_terms": ["invoices"]})
→ accounting-invoices-list, accounting-invoices-create, accounting-invoices-get, ...
describe_tool_input({"name": "accounting-invoices-list"})
→ Full JSON Schema with all parameters
execute_tool({"name": "accounting-invoices-list", "input": {"request": {"limit": 10}}})
→ Invoice data from the connected accounting systemYou can combine dynamic mode with a scope filter:
{
"mcpServers": {
"apideck": {
"command": "node",
"args": ["dist/bin/mcp.js", "--mode", "dynamic", "--scope", "read"],
"env": { "APIDECK_API_KEY": "...", "APIDECK_CONSUMER_ID": "...", "APIDECK_APP_ID": "..." }
}
}
}Code mode exposes two tools instead of 330+. Designed for agents that prefer calling endpoints as methods rather than tool calls:
apideck_search — find endpoints by substring, returns camelCase method names
apideck_run — execute a JS script with apideck.<methodName> bound to live endpoint dispatchers, sandboxed in node:vm
apideck_search("invoices")
→ {
count: 4,
endpoints: [
{ name: "accounting-invoices-list", method: "accountingInvoicesList" },
{ name: "accounting-invoices-create", method: "accountingInvoicesCreate" },
{ name: "accounting-invoices-get", method: "accountingInvoicesGet" },
{ name: "accounting-invoices-delete", method: "accountingInvoicesDelete" }
]
}
apideck_run({
script: "return await apideck.accountingInvoicesList({ request: { limit: 5 } })"
})
→ Invoice data from the connected accounting systemThe sandbox strips process, require, fs, child_process, and other Node globals — scripts only have access to the apideck object.
Filter tools by HTTP method class:
Scope | HTTP methods | Flag |
| GET, HEAD |
|
| POST, PUT, PATCH |
|
| DELETE |
|
# OpenAI Agents SDK
from agents import Agent
from agents.mcp import MCPServerHTTP
agent = Agent(
name="Apideck Agent",
mcp_servers=[MCPServerHTTP(
url="https://mcp.apideck.dev/mcp",
headers={
"x-apideck-api-key": "...",
"x-apideck-consumer-id": "...",
"x-apideck-app-id": "..."
}
)]
)# Pydantic AI
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP
agent = Agent("anthropic:claude-sonnet-4-5", mcp_servers=[
MCPServerHTTP(
url="https://mcp.apideck.dev/mcp",
headers={
"x-apideck-api-key": "...",
"x-apideck-consumer-id": "...",
"x-apideck-app-id": "..."
}
)
])# LangChain / LangGraph
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"apideck": {
"url": "https://mcp.apideck.dev/mcp",
"transport": "streamable_http",
"headers": {
"x-apideck-api-key": "...",
"x-apideck-consumer-id": "...",
"x-apideck-app-id": "..."
}
}
})
tools = await client.get_tools()pnpm install
pnpm build
# Dynamic mode (default)
APIDECK_API_KEY=... APIDECK_CONSUMER_ID=... APIDECK_APP_ID=... node dist/bin/mcp.js start
# Static mode (all 330 tools)
APIDECK_API_KEY=... node dist/bin/mcp.js start --mode static
# Code mode
APIDECK_API_KEY=... node dist/bin/mcp.js start --mode code
# Read-only
APIDECK_API_KEY=... node dist/bin/mcp.js start --scope read# OpenAI Agents SDK (local stdio)
from agents import Agent
from agents.mcp import MCPServerStdio
mcp = MCPServerStdio(name="apideck", params={
"command": "node",
"args": ["dist/bin/mcp.js", "start", "--mode", "dynamic"],
"env": {
"APIDECK_API_KEY": "...",
"APIDECK_CONSUMER_ID": "...",
"APIDECK_APP_ID": "..."
}
})
agent = Agent(name="Apideck Agent", mcp_servers=[mcp])The runtime automatically retries failed requests so transient errors don't surface to your agent:
Retried status codes: 408, 500, 502, 503, 504
Retried network errors: ECONNRESET, ECONNREFUSED, ETIMEDOUT, and similar
Strategy: exponential backoff, up to 4 attempts, capped at 30 s
Idempotency: retries only fire on GET, HEAD, PUT, DELETE, OPTIONS, TRACE — POST/PATCH are not retried automatically
File Storage endpoints that return images or audio send them as native MCP content blocks rather than base64 strings in JSON:
{ "type": "image", "data": "<base64>", "mimeType": "image/png" }
{ "type": "audio", "data": "<base64>", "mimeType": "audio/mpeg" }Agents that support multi-modal MCP content (Claude, GPT-4o) receive the raw bytes — no extra decoding step needed.
MIT
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
A Model Context Protocol server for Wix AI tools
MCP server for interacting with the Supabase platform
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/apideck-libraries/mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
