Wir machen KI in Vertrieb und Marketing wirksam: Wir verstehen Ihren Engpass, bauen die Lösung selbst und begleiten sie bis zum Ergebnis. Made in Germany, DSGVO-konform.
This listing identifies a third-party MCP server. MCPBundles is not affiliated with, sponsored by, or endorsed by the service or its operator unless stated on this page.
This server may ask you to sign in when your AI client connects.
Last probed Nov 3, 2026 · api.gotoki.ai
54tools discovered
For AI agents — MCPBundles Directory API
For MCP client apps (human connect):
MCP connect URL: https://api.gotoki.ai/mcp
Skill page: https://www.mcpbundles.com/skills/gotoki-mcp-23ffaef0b6
Explore capabilities (54)
read 11
write 10
other 4
Showing 25 of 54
Showing 25 of 54 tools from the public preview. Connect the server to inspect the full live tool list.
List6
Get5
Update4
Create3
Delete3
Set2
Other capabilities2
List Agents
read
list_agents
List all voice agents that belong to the authenticated user. Returns agent id, title, created date, last call date, call count, minutes used, license fee, and cost per minute.
List Agents — List all voice agents that belong to the authenticated user. Returns agent id, title, created date, last call date, call count, minutes used, license fee, and cost per minute.
Get Agent — Get full details for a single agent by its ID, including configuration, system prompt, greeting message, phone routing, advanced settings, and embed config.
Create Agent — Create a new voice agent. Admin only. Requires a title and user_id: the customer (any user, client or admin) the agent is created for. Agents have separate prompts and greetings for inbound and outbound calls: inbound_system_prompt / outbound_system_prompt are the instructions the agent follows, and inbound_greeting_message / outbound_greeting_message are the opening lines spoken at the start of a call. The legacy single 'system_prompt' / 'greeting_message' fields are deprecated — do not use the
Update Agent — Update an existing agent. Pass an 'updates' dict with only the fields to change. For prompts and greetings use the inbound/outbound fields — inbound_system_prompt, outbound_system_prompt, inbound_greeting_message, outbound_greeting_message. The legacy 'system_prompt' and 'greeting_message' fields are deprecated; do not write to them. Other updatable fields include title, description, voicemail_message, voicemail_detection_enabled, voicemail_detection_prompt, evaluation_prompt, timezone, phone ro
Delete Agent — Permanently delete an agent by its ID. Admin only.
List Prompt Versions — List the prompt version history for an agent. Returns each version with its timestamp so you can review or restore a prior prompt.
Get Agent Webhook — Get the webhook configuration for an agent (the URL that Gotoki will POST call events to).
Set Agent Webhook — Set or update the webhook URL for an agent.
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
Wir machen KI in Vertrieb und Marketing wirksam: Wir verstehen Ihren Engpass, bauen die Lösung selbst und begleiten sie bis zum Ergebnis. Made in Germany, DSGVO-konform.
How do I connect GO TO KI to my AI agent?
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
How many tools does GO TO KI provide?
Operate this server?
Request removal if you do not want GO TO KI listed here, or claim the listing if you want to manage it on MCPBundles.
Operate GO TO KI?
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.
MCPBundles publishes this directory for MCP discovery. Except where we host or operate an offering, third-party services run under their own terms. Product and company names on this page are used in a descriptive, identifying way (including under nominative fair use where applicable); they remain the property of their owners. Nothing here grants you rights in those marks, and nothing here is an offer to sell a third party's services. Terms · Request removal
More in marketing
Other MCP servers in this category from the directory index
— List all variables ({{...}} placeholders) defined on an agent. Variables are used to inject dynamic values into calls.
Get Agent Variable — Get a single variable by its ID for a given agent.
Create Agent Variable — Create a new variable ({{...}} placeholder) on an agent. Provide 'name' and optionally a 'default_value'. template_id is optional — when omitted, the default static-variable template is used (same as the dashboard's standard variable creation).
Update Agent Variable — Update a static variable's name and/or default value. Only static (and custom) variables are editable; Pipedrive standard variables are read-only. Provide the new 'name' and/or 'default_value' — omit a field to leave it unchanged.
Delete Agent Variable — Delete a variable by its ID.
List Evaluation Labels — List all evaluation labels for an agent. Labels classify calls (e.g. 'Interested', 'Not Interested') based on rules. Each label carries two classification fields - read them instead of guessing from the label name, which is written in the customer's own language. 'outcome_polarity' ('positive' | 'neutral' | 'negative') is what reporting counts as a conversion. 'reach_status' ('reached' | 'not_reached' | 'unknown') is whether a person was actually on the line. They are independent of each other a
Create Evaluation Label — Create an evaluation label for an agent. Provide label_data with keys: name, description, classification_rule, and optionally outcome_polarity ('positive' | 'neutral' | 'negative', defaults to 'neutral') and reach_status ('reached' | 'not_reached' | 'unknown', defaults to 'unknown'). Set outcome_polarity to 'positive' only for outcomes that should count as a conversion, and reach_status to 'reached' only when the label means a person was on the line - voicemail, IVR and bot pickups are 'not_reac
Update Evaluation Label — Update an evaluation label. Provide only the fields to change. Settable keys: name, description, classification_rule, sort_order, outcome_polarity ('positive' | 'neutral' | 'negative'), reach_status ('reached' | 'not_reached' | 'unknown'). Changing either re-scores every past call carrying this label in campaign reporting - both are read live, not stamped onto the call - and changes nothing about retries or call status.
Delete Evaluation Label — Delete an evaluation label by its ID.
List Available Tools — List all available tools on the platform that can be assigned to an agent. Includes tools like Redirect Call, Custom Function, Outlook Calendar, etc. Optionally filter by search term or category.
List Agent Tools — List all tools currently assigned to an agent, along with their configuration.
Assign Tool To Agent — Assign a tool to an agent by tool ID. Use list_available_tools to find the tool_id first.
Unassign Tool From Agent — Remove (unassign) a tool from an agent by tool ID.
Get Agent Tool Config — Get the current configuration for a specific tool assigned to an agent.
Update Agent Tool Config — Update the configuration for a tool assigned to an agent. config is a list of field objects, each with keys: type, required, title, api_key, value, description.
Get Evaluation Prompt — Get the evaluation prompt for an agent. This is the context used by the AI to evaluate and label calls.
Set Evaluation Prompt — Set or update the evaluation prompt for an agent. The evaluation prompt gives the AI context to classify calls with evaluation labels.
Showing the first 25 tools — full list and schemas: Directory API.
MCPBundles probed 54 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
What authentication does GO TO KI require?
GO TO KI may require signing in to the provider before tools can run. Connect through MCPBundles or your MCP client and complete any provider login when prompted.
Don't want this listed?
Request removal from the MCPBundles directory. We stop publishing this listing on mcpbundles.com.
MCPBundles is an independent platform built on the open Model Context Protocol standard. MCPBundles is not affiliated with, sponsored by, or endorsed by Anthropic PBC.