Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Marketo MCP Server find lead by email test@example.com"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Python MCP server for the Marketo REST API described in as per Marketo API Documentation
Set these environment variables before running:
MARKETO_BASE_URL - Marketo instance URL, for example https://<munchkin-id>.mktorest.com
MARKETO_CLIENT_ID - OAuth client id
MARKETO_CLIENT_SECRET - OAuth client secret
Optional:
MARKETO_TIMEOUT - Request timeout in seconds, default 30
MARKETO_ACCESS_TOKEN - Pre-fetched bearer token to skip OAuth token retrieval
Related MCP server: marketo-mcp-server
cd marketo-mcp
python -m venv .venv
source .venv/bin/activate
pip install -e .
marketo-mcpThe server exposes tools for the Marketo operations in the OpenAPI spec, including:
authentication token retrieval
leads search, create/update, delete, and describe
list membership operations
campaign listing, triggering, and scheduling
activity queries
company and opportunity operations
asset listing and retrieval
usage and error stats
Inputs: list_id (required), input (required). Returns: result
Inputs: input (required), action, dedupe_by. Returns: result
Inputs: input (required), action, lookup_field. Returns: result
Inputs: input (required), action, dedupe_by. Returns: result
Inputs: input (required). Returns: result
Inputs: no named parameters. Returns: result
Inputs: no named parameters. Returns: result
Inputs: no named parameters. Returns: result
Get an OAuth access token using client credentials.
Inputs: client_id (required), client_secret (required). Returns: result
Inputs: activity_type_ids (required), next_page_token (required), lead_ids, batch_size. Returns: result
Inputs: no named parameters. Returns: result
Inputs: id, name, program_name, batch_size. Returns: result
Inputs: no named parameters. Returns: result
Inputs: no named parameters. Returns: result
Inputs: email_id (required). Returns: result
Inputs: email_id (required). Returns: result
Inputs: max_return, offset, status, folder. Returns: result
Inputs: root, max_depth, max_return, offset. Returns: result
Inputs: max_return, offset, status. Returns: result
Inputs: max_return, offset, status. Returns: result
Inputs: lead_id (required), fields. Returns: result
Inputs: fields (required), next_page_token (required), batch_size. Returns: result
Inputs: list_id (required), fields, batch_size. Returns: result
Inputs: id, name, batch_size. Returns: result
Inputs: since_datetime (required). Returns: result
Inputs: program_id (required). Returns: result
Inputs: max_return, offset, filter_type, filter_values. Returns: result
Inputs: folder_id (required), folder_type (required). Returns: result
Inputs: list_id (required), input (required). Returns: result
Inputs: campaign_id (required), input (required). Returns: result
Inputs: filter_type (required), filter_values (required), fields. Returns: result
Inputs: filter_type (required), filter_values (required), fields, batch_size, +1 more. Returns: result
Inputs: filter_type (required), filter_values (required), fields. Returns: result
Inputs: campaign_id (required), input (required). Returns: result
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 34 tools
Many tools have distinct names, but several pairs like describe_leads vs get_lead_by_id vs search_leads could cause ambiguity. The lack of descriptions exacerbates confusion, though the names are specific enough to differentiate with context.
All tools follow a consistent snake_case verb_noun pattern, with verbs like get, create_update, delete, describe, search, add, remove, schedule, trigger. No mixing of conventions.
34 tools is on the high side, but Marketo is a broad platform. The count could be trimmed, but it remains within a plausible range for a comprehensive integration.
While many entities are covered, significant operations are missing: no create/update/delete for emails, campaigns, programs, folders, forms, or landing pages. Update and delete for companies/opportunities are absent, leaving gaps in lifecycle management.
Marketo MCP server for AI. 130 tools to operate Marketo from Claude, Cursor, or ChatGPT.
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
API-first CRM for LLMs - contacts, companies, deals and activities over a native MCP server.
MCP server for customer-io
