mirror of
https://github.com/dograh-hq/dograh.git
synced 2026-06-07 07:55:16 +02:00
75839f9de5
* feat(mcp): generic MCP tool source with per-node function filtering
Adds a Model Context Protocol tool category: connect a customer MCP
server and expose its tools to the agent, with optional per-node
allow-listing of individual MCP functions.
- ToolCategory.MCP enum + alembic migration
- MCP definition validator and collision-safe function-name namespacing
- McpToolSession wrapper: graceful-degrade, per-call open/close lifecycle
- CustomToolManager MCP branch (schemas + proxy handlers)
- Per-node mcp_tool_filters threaded through DTO/graph/engine
- Best-effort discovered_tools catalog cache + POST /tools/{uuid}/mcp/refresh
- UI: MCP create/edit config, tabbed ToolSelector with per-node toggles
* feat: refactor for code standardisation and documentation
---------
Co-authored-by: Abhishek Kumar <abhishek@a6k.me>
40 lines
2 KiB
Text
40 lines
2 KiB
Text
---
|
|
title: "Tools"
|
|
description: "Extend your voice agent's capabilities by giving it tools to perform actions during live conversations."
|
|
---
|
|
|
|
Tools let your AI agent take actions during a conversation — transfer calls, end calls, call external APIs, or invoke remote MCP servers — based on the context of the conversation and your prompt instructions.
|
|
|
|
When a tool is attached to a workflow node, the LLM decides **when** to invoke it and **what parameters** to pass, based on the user's spoken intent and your node-level instructions.
|
|
|
|
## Tool Types
|
|
|
|
Dograh provides two categories of tools:
|
|
|
|
### Built-in Tools
|
|
|
|
Pre-configured tools that handle common telephony operations out of the box:
|
|
|
|
- [**Call Transfer**](/voice-agent/tools/call-transfer) — Transfer the active call to a phone number or SIP endpoint
|
|
- [**End Call**](/voice-agent/tools/end-call) — Terminate the call when the conversation is complete
|
|
|
|
### Custom Tools
|
|
|
|
Tools you define to integrate with any external system:
|
|
|
|
- [**HTTP API**](/voice-agent/tools/http-api) — Call any REST API endpoint during a conversation (e.g., CRM updates, data lookups, triggering automations)
|
|
- [**MCP Tool**](/voice-agent/tools/mcp-tool) — Connect an external MCP server and expose its remote tools to the LLM during a conversation
|
|
|
|
## How Tools Work
|
|
|
|
1. You **define** a tool with a name, description, and parameters
|
|
2. You **attach** the tool to one or more workflow nodes
|
|
3. During a call, the LLM reads your node prompt, the tool description, and the caller's intent to decide whether to invoke the tool
|
|
4. The tool executes and returns a result that the agent can use to continue the conversation
|
|
|
|
## Best Practices
|
|
|
|
- **Attach only relevant tools to each node** — fewer tools means more reliable invocations
|
|
- **Write clear tool descriptions** — the LLM uses these to decide when to call the tool
|
|
- **Guide the LLM in your node prompt** — explicitly describe when a tool should be used
|
|
- **Test tool behavior** — verify your agent invokes tools at the right moments using web or phone calls
|