Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
docs: explain input_requests before mentioning MCP elicitation
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Mukund committed
Oct 15, 2026 at 18:12 UTC
8bec4d90ec14659f07a5dec2b6b1c38c5f029077
1 file changed
+5
-1
docs/content/docs/approvals.mdx
+5
-1
@@ -122,7 +122,7 @@ try {
122
</Tab>
123
</Tabs>
124
125
-`input_requests` holds the [MCP elicitations](https://modelcontextprotocol.io/specification/2026-07-28/client/elicitation) for the user, keyed by ID. One tool execution can return several of them, for example when the agent runs several tools at once with `COMPOSIO_MULTI_EXECUTE_TOOL`. Answer all of them when you send the call again:
125
+The error's `input_requests` holds the questions to ask the user, keyed by ID. Each question has a `message` describing the tool call, and a `requested_schema` describing the answer the user can give:
126
127
```json
128
{
@@ -151,6 +151,10 @@ try {
151
152
Show the user the `message` and a form built from `requested_schema`. Build the form from the schema, since the choices vary between questions.
153
154
+One tool execution can return several questions, for example when the agent runs several tools at once with `COMPOSIO_MULTI_EXECUTE_TOOL`. Answer all of them when you send the call again.
155
+
156
+The questions follow the format of [MCP elicitation](https://modelcontextprotocol.io/specification/2026-07-28/client/elicitation) requests, so you can reuse an existing elicitation UI.
157
+
158
## Sending the answer
159
160
Send the same call again with the user's answers: