ConvertAPI MCP

Live

API KEY

AUTOMATION

Developer Tools

Connect your AI agent to ConvertAPI MCP to convert, merge, split, and transform files across 200+ formats including PDF, Word, Excel, images, and more. Agents can discover available converters, retrieve supported parameters, and execute file conversions programmatically — all scoped to the authorizing account.

  • Acts as the user: All file conversion operations execute under the account that authorized the agent, so every converted document and transformation is traceable to the account owner.
  • Credentials stay vaulted: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: Permissions enforced per-user. 90-day audit trail.
ConvertAPI MCP
agent · Acme Q3
Run
Convert this DOCX report to PDF with landscape orientation.
S
convertapimcp_convert
85ms
ConvertAPI MCP agent
Successfully converted report.docx to PDF with landscape orientation — the file is ready at converted_output/report.pdf.
Sources: 1 file converted
convertapimcpmcp
1 file
18:29
Message Claude...

Tools your developer agent reaches for on ConvertAPI MCP, scoped per user.

CALL ANY TOOL
Four tools cover the full ConvertAPI workflow — discovering converters, inspecting supported parameters, filtering by tags, and executing file format conversions across 200+ formats.
convertapimcp_convert
Convert file format
Dynamically converts a file from one format to another using ConvertAPI with OpenAPI-driven parameter validation.
Parameters
Name
Type
Required
Description
fromFormat
string
Required
Source file format (e.g. 'docx', 'xlsx', 'jpg').
toFormat
string
Required
Target file format (e.g. 'pdf', 'png', 'html').
parameters
object
Optional
Conversion settings as key-value pairs (e.g. PageSize, PageOrientation, Quality).
fileParameters
object
Optional
Files to convert with associated parameter names as key-value pairs.
outputDirectory
string
Optional
Destination folder where converted files will be stored (local mode only).
convertapimcp_get_conversion_parameters
Get conversion parameters
convertapimcp_get_converters_by_tags
Get converters by tags
convertapimcp_search_converters
Search converters
Build your Agent
Same auth pattern across every framework.
Python · LlamaIndex
from langchain_mcp_adapters.client import MultiServerMCPClient
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="convertapimcp")

mcp = MultiServerMCPClient({
"convertapimcp": {
"url": "https://mcp.scalekit.com/convertapimcp",
"headers": {"Authorization": "Bearer " + token}
}
})
tools = await mcp.get_tools()
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "convertapimcp" });

const openai = new OpenAI();
// Connect to MCP at https://mcp.scalekit.com/convertapimcp
// Pass: Authorization: Bearer + token
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "convertapimcp" });

const anthropic = new Anthropic();
// Connect to MCP at https://mcp.scalekit.com/convertapimcp
// Pass: Authorization: Bearer + token
from google.adk.agents import LlmAgent
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="convertapimcp")
# Connect to MCP at https://mcp.scalekit.com/convertapimcp
# Pass: Authorization: Bearer + token
Try these prompts
Paste any prompt into your agent to get started.
Discover & explore
Copy the prompt
Copied
Find all available converters that support PDF as an output format.
Copy the prompt
Copied
What parameters are available when converting a DOCX file to PDF?
Convert & transform
Copy the prompt
Copied
Convert this Word document to a PDF with A4 page size and portrait orientation.
Copy the prompt
Copied
Batch convert all JPEG images in this folder to PNG format at 300 DPI resolution.
SEE HOW AUTH WORKS
User authorises once. Every agent call after uses their token with scope enforcement.
1
Authorize
Your user connects
ConvertAPI MCP
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
ConvertAPI MCP
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
ConvertAPI MCP
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
ConvertAPI MCP
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
See the same per-user auth pattern across other connectors.
No items found.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
Other connector libraries treat auth as a demo afterthought.
01.
Shared tokens break per-user analytics
A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential.
// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access ConvertAPI MCP as the user or as a shared key?
Scalekit resolves a per-user credential for each call. The ConvertAPI MCP audit log shows the real user identity, not a shared service account.
Where is the ConvertAPI MCP token stored?
In Scalekit's AES-256 encrypted vault, isolated per tenant. Tokens are auto-refreshed before expiry and revocable from a single dashboard without code changes.
Can I limit what the agent is allowed to do in ConvertAPI MCP?
Pass a toolNames filter to listScopedTools. Scalekit enforces the allowed set before every API call — the agent cannot invoke tools outside the approved list.
What happens when a user revokes ConvertAPI MCP access?
The token is invalidated at the next tool call. The agent fails closed rather than falling back to a shared key. Other users are unaffected and the revocation event is logged with a timestamp.
ConvertAPI charges per conversion — how do I prevent one user's agent from consuming another tenant's quota?
Because Scalekit resolves a per-user credential for each call, conversions run under the authorizing account's ConvertAPI balance. One tenant's agent cannot draw from another tenant's credits, and you can revoke a specific user's token to halt further usage without affecting other accounts.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""convertapimcp"": {
""url"": ""https://mcp.scalekit.com/convertapimcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.convertapimcp]
url = ""https://mcp.scalekit.com/convertapimcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""convertapimcp"": {
""url"": ""https://mcp.scalekit.com/convertapimcp"",
""type"": ""http""
}
}
}