Apideck MCP Server

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.

Quick Connect

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.

[!NOTE] Learn more about Desktop 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 start

The 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"
      }
    }
  }
}

---

Claude Desktop (.mcpb plugin bundle)

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.

---

Tools

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

Workflow tools

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
apideck-month-end-close-check	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

---

Hosted

The server is live at:

https://mcp.apideck.dev/mcp

Pass credentials via headers:

Header	Description
x-apideck-api-key	Your Apideck API key
x-apideck-consumer-id	The end-user / customer ID in your app (optional — see below)
x-apideck-app-id	Your Apideck application ID

Consumer scoping (optional)

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.

Locking identity (opt-in)

To pin identity to the boot header/env and stop agents from switching consumer or connection per call, start with --lock-identity (CLI) or append ?lock_identity=true (hosted). Locked calls ignore per-call consumer_id / service_id arguments. Off by default. Vault consumer tools that take consumer_id as a path parameter (e.g. vault-consumers-one) only accept the locked consumer; any other value, or no locked consumer, is refused. service_id path parameters (e.g. vault-connections-one) are unaffected.

---

Three Modes

Mode	Tools exposed	Initial tokens	Best for
dynamic (default)	4 meta-tools	~1,300	General-purpose agents, token-sensitive contexts
static	All 330 tools	~35–55K	Focused agents doing a specific API
code	apideck_search + apideck_run	~600	Agents that call endpoints programmatically via JS

Dynamic mode

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 system

You 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

Code mode exposes two tools instead of 330+. Designed for agents that prefer calling endpoints as methods rather than tool calls:

1. apideck_search — find endpoints by substring, returns camelCase method names
2. 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 system

The sandbox strips process, require, fs, child_process, and other Node globals — scripts only have access to the apideck object.

---

Scopes

Filter tools by HTTP method class:

Scope	HTTP methods	Flag
read	GET, HEAD	--scope read
write	POST, PUT, PATCH	--scope write
destructive	DELETE	--scope destructive

Repeat the flag to combine scopes (--scope read --scope write). On the hosted endpoint use a comma-separated query param: ?scopes=read,write. Invalid or empty values are rejected (CLI parse error / HTTP 400). Scopes apply in every mode, including code.

---

Connect from Any Agent Framework

Remote (hosted — no local install)

# 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()

Local stdio (for development)

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])

---

Reliability

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

Binary Content

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.

---

License

MIT