菜单
Calls MCP tools directly from Rasa flow steps. Use when invoking an MCP tool via a call step, mapping slot values to tool parameters, or extracting tool results into slots. This replaces custom action code for simple API integrations.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | rasa-calling-mcp-tools-from-flows |
| description | Calls MCP tools directly from Rasa flow steps. Use when invoking an MCP tool via a call step, mapping slot values to tool parameters, or extracting tool results into slots. This replaces custom action code for simple API integrations. |
| license | Apache-2.0 |
| metadata | {"author":"rasa","version":"0.1.0","rasa_version":">=3.14.0","docs-url":"https://rasa.com/docs/pro/build/mcp-integration"} |
MCP tools can be invoked directly from flow steps using a call step with explicit
input/output mappings. This replaces the need for custom action code when you only need
to call an external API.
MCP servers must be defined in endpoints.yml before calling their tools. See the
rasa-configuring-mcp-server skill for server setup and authentication.
This feature is in beta and available starting from Rasa 3.14.0.
Use an MCP tool call when:
Use a custom action instead when:
See rasa-writing-custom-actions for custom action guidance.
endpoints.yml
(see rasa-configuring-mcp-server skill).call step with mcp_server and mapping
(see "Calling an MCP tool from a flow").Use a call step with mcp_server and mapping to invoke a tool directly.
| Key | Required | Description |
|---|---|---|
call | yes | Tool name as exposed by the MCP server |
mcp_server | yes | Must exactly match a name in endpoints.yml. Fails at runtime if mismatched |
mapping.input | yes | Maps slot values to tool parameters. Each entry: param (tool parameter name) + slot (Rasa slot name) |
mapping.output | yes | Maps tool results back to slots. Each entry: slot (target slot) + value (Jinja2 expression to extract the result) |
flows:
buy_order:
description: helps users place a buy order for a particular stock
steps:
- collect: stock_name
- collect: order_quantity
- action: check_feasibility
next:
- if: slots.order_feasible is True
then:
- call: place_buy_order
mcp_server: trade_server
mapping:
input:
- param: ticker_symbol
slot: stock_name
- param: quantity
slot: order_quantity
output:
- slot: order_status
value: result.structuredContent.order_status.success
- else:
- action: utter_invalid_order
next: END
MCP tools return results in one of two formats. Handle both in your output mapping.
When the tool defines an output schema, Rasa returns structured data. Access specific
values using dot notation in the value field:
# Tool returns: {"result": {"structuredContent": {"order_status": {"success": true, "order_id": "abc123"}}}}
output:
- slot: order_status
value: result.structuredContent.order_status.success
- slot: order_id
value: result.structuredContent.order_status.order_id
When the tool has no output schema, the entire result is a serialized string. Capture it in a single slot for downstream processing:
# Tool returns: {"result": {"content": [{"type": "text", "text": "{\"order_status\": ...}"}]}}
output:
- slot: order_data
value: result.content
mcp_server value in a flow call step must
exactly match a name in endpoints.yml. A typo means the call fails at runtime
with no compile-time warning.call doesn't exist on the
referenced MCP server, the call fails at runtime.result.content, not as result.structuredContent.
Always account for both formats.Use when a user wants to evaluate or test a Rasa assistant using the eval scenario framework — at any stage of the process: setting up the evaluation infrastructure for the first time, deciding which scenario types to cover for a flow, writing or generating scenario YAML files, learning about supported assertion types or how to write good success criteria, running goal-driven simulations where an LLM plays the user role against a live Rasa bot, or analyzing whether existing scenarios are comprehensive. Covers both the authoring side ("write scenarios", "generate evals", "help me write criteria") and the execution side ("simulate a conversation", "run my eval scenarios"). Not for scripted end-to-end tests, unit tests, NLU training, or general Rasa bot development.
Builds skills (capabilities) for a Rasa CALM assistant. Use when the user asks to create, add, or build a skill, capability, or feature for their Rasa assistant.
Configures config.yml and endpoints.yml for Rasa CALM assistants. Covers pipeline (command generators, flow retrieval), policies (FlowPolicy), action endpoint, and language settings. Use when setting up a new project or modifying pipeline components.
Configures model_groups in endpoints.yml for LLM and embedding providers. Covers single and multi-deployment setups, routing strategies, failover, self-hosted models, and caching. Use when adding or changing LLM providers or setting up multi-LLM routing.
Enables and configures LLM-powered Contextual Response Rephraser in Rasa CALM. Covers endpoints.yml setup, per-response metadata, and prompt customization. Use when setting up or tuning the Contextual Response Rephraser.
Adds knowledge base search to a Rasa CALM assistant using EnterpriseSearchPolicy, connects vector stores (Faiss, Milvus, Qdrant), and configures generative or extractive search modes. Use when setting up RAG, connecting a vector store, overriding pattern_search, or implementing a custom information retriever.