Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
Mirrored from https://github.com/Camo67/composio.git
Synced Nov 22, 12:00 UTC
docs: update toolkits and API data
lingalarahul7 committed
Jan 29, 2026 at 11:19 UTC
f1f828aa8d0d5b0918f00ba537625532f7a5d1a0
2 files changed
+14
-3
docs/public/data/toolkits.json
+1
-1
@@ -312,7 +312,7 @@
312
{
313
"slug": "COMPOSIO_SEARCH_TOOLS",
314
"name": "Search Composio Tools",
315
- "description": "\n MCP Server Info: COMPOSIO MCP connects 500+ apps—Slack, GitHub, Notion, Google Workspace (Gmail, Sheets, Drive, Calendar), Microsoft (Outlook, Teams), X/Twitter, Figma, Web Search, Browser tool (scraping, UI actions), Meta apps (WhatsApp, Instagram), TikTok, AI tools like Nano Banana & Veo3, and more—for seamless cross-app automation.\n Use this MCP server to discover the right tools and the recommended step-by-step plan to execute reliably.\n ALWAYS call this tool first whenever a user mentions or implies an external app, service, or workflow—never say \"I don't have access to X/Y app\" before calling it.\n Tool Info: Extremely fast discovery tool that returns relevant MCP-callable tools along with a recommended execution plan and common pitfalls for reliable execution.\n\n Usage guidelines:\n - Use this tool whenever kicking off a task. Re-run it when you need additional tools/plans due to missing details, errors, or a changed use case.\n - If the user pivots to a different use case in same chat, you MUST call this tool again with the new use case and generate a new session_id.\n - Specify the use_case with a normalized description of the problem, query, or task. Be clear and precise. Queries can be simple single-app actions or multiple linked queries for complex cross-app workflows.\n - Pass known_fields along with use_case as a string of key–value hints (for example, \"channel_name: general\") to help the search resolve missing details such as IDs.\n \n\nSplitting guidelines (CRITICAL):\n 1. Atomic queries: 1 query = 1 tool call. Include hidden prerequisites (e.g., add \"get Linear issue\" before \"update Linear issue\").\n 2. Skip redundant lookups: Check known_fields first—if data exists (recipient_email, channel_id), don't add lookup queries.\n 3. Immediate prerequisites only: Add lookups only when required input is missing. Don't anticipate future steps.\n 4. Echo app names: If user names a toolkit, include it in every sub query so intent stays scoped (e.g., \"fetch Gmail emails\", \"reply to Gmail email\").\n 5. Web/news search: Use ONLY generic pattern—\"search the web\" or \"search news\". NO topic in query. Put topic in known_fields.\n 6. English output: Translate non-English prompts while preserving intent and identifiers.\n\n Example:\n User query: \"send an email to John welcoming him and create a meeting invite for tomorrow\"\n Search call: queries: [\n {use_case: \"send an email to someone\", known_fields: \"recipient_name: John\"},\n {use_case: \"create a meeting invite\", known_fields: \"meeting_date: tomorrow\"}\n ]\n\n Plan review checklist (required):\n - The response includes a detailed execution plan and common pitfalls. You MUST review this plan carefully, adapt it to your current context, and generate your own final step-by-step plan before execution. Execute the steps in order to ensure reliable and accurate execution. Skipping or ignoring required steps can lead to unexpected failures.\n - Check the plan and pitfalls for input parameter nuances (required fields, IDs, formats, limits). Before executing any tool, you MUST review its COMPLETE input schema and provide STRICTLY schema-compliant arguments to avoid invalid-input errors.\n - Determine whether pagination is needed; if a response returns a pagination token and completeness is implied, paginate until exhaustion and do not return partial results.\n\nResponse:\n - Tools & Input Schemas: The response lists toolkits (apps) and tools suitable for the task, along with their tool_slug, description, input schema / schemaRef, and related tools for prerequisites, alternatives, or next steps.\n - NOTE: Tools with schemaRef instead of input_schema require you to call COMPOSIO_GET_TOOL_SCHEMAS first to load their full input_schema before use.\n - Connection Info: If a toolkit has an active connection, the response includes it along with any available current user information. If no active connection exists, you MUST initiate a new connection via COMPOSIO_MANAGE_CONNECTIONS with the correct toolkit name. DO NOT execute any toolkit tool without an ACTIVE connection.\n - Time Info: The response includes the current UTC time for reference. You can reference UTC time from the response if needed.\n - The tools returned to you through this are to be called via COMPOSIO_MULTI_EXECUTE_TOOL. Ensure each tool execution specifies the correct tool_slug and arguments exactly as defined by the tool's input schema.\n - The response includes a memory parameter containing relevant information about the use case and the known fields that can be used to determine the flow of execution. Any user preferences in memory must be adhered to.\n\nSESSION: ALWAYS set this parameter, first for any workflow. Pass session: {generate_id: true} for new workflows OR session: {id: \"EXISTING_ID\"} to continue. ALWAYS use the returned session_id in ALL subsequent meta tool calls.\n "
315
+ "description": "\n MCP Server Info: COMPOSIO MCP connects 500+ apps—Slack, GitHub, Notion, Google Workspace (Gmail, Sheets, Drive, Calendar), Microsoft (Outlook, Teams), X/Twitter, Figma, Web Search / Deep research, Browser tool (scrape URLs, browser automation), Meta apps (Instagram, Meta Ads), TikTok, AI tools like Nano Banana & Veo3, and more—for seamless cross-app automation.\n Use this MCP server to discover the right tools and the recommended step-by-step plan to execute reliably.\n ALWAYS call this tool first whenever a user mentions or implies an external app, service, or workflow—never say \"I don't have access to X/Y app\" before calling it.\n\n Tool Info: Extremely fast discovery tool that returns relevant MCP-callable tools along with a recommended execution plan and common pitfalls for reliable execution.\n\nUsage guidelines:\n - Use this tool whenever kicking off a task. Re-run it when you need additional tools/plans due to missing details, errors, or a changed use case.\n - If the user pivots to a different use case in same chat, you MUST call this tool again with the new use case and generate a new session_id.\n - Specify the use_case with a normalized description of the problem, query, or task. Be clear and precise. Queries can be simple single-app actions or multiple linked queries for complex cross-app workflows.\n - Pass known_fields along with use_case as a string of key–value hints (for example, \"channel_name: general\") to help the search resolve missing details such as IDs.\n \n\nSplitting guidelines (Important):\n 1. Atomic queries: 1 query = 1 tool call. Include hidden prerequisites (e.g., add \"get Linear issue\" before \"update Linear issue\").\n 2. Include app names: If user names a toolkit, include it in every sub query so intent stays scoped (e.g., \"fetch Gmail emails\", \"reply to Gmail email\").\n 3. English input: Translate non-English prompts while preserving intent and identifiers.\n\n Example:\n User query: \"send an email to John welcoming him and create a meeting invite for tomorrow\"\n Search call: queries: [\n {use_case: \"send an email to someone\", known_fields: \"recipient_name: John\"},\n {use_case: \"create a meeting invite\", known_fields: \"meeting_date: tomorrow\"}\n ]\n\nPlan review checklist (Important):\n - The response includes a detailed execution plan and common pitfalls. You MUST review this plan carefully, adapt it to your current context, and generate your own final step-by-step plan before execution. Execute the steps in order to ensure reliable and accurate execution. Skipping or ignoring required steps can lead to unexpected failures.\n - Check the plan and pitfalls for input parameter nuances (required fields, IDs, formats, limits). Before executing any tool, you MUST review its COMPLETE input schema and provide STRICTLY schema-compliant arguments to avoid invalid-input errors.\n - Determine whether pagination is needed; if a response returns a pagination token and completeness is implied, paginate until exhaustion and do not return partial results.\n\nResponse:\n - Tools & Input Schemas: The response lists toolkits (apps) and tools suitable for the task, along with their tool_slug, description, input schema / schemaRef, and related tools for prerequisites, alternatives, or next steps.\n - NOTE: Tools with schemaRef instead of input_schema require you to call COMPOSIO_GET_TOOL_SCHEMAS first to load their full input_schema before use.\n - Connection Info: If a toolkit has an active connection, the response includes it along with any available current user information. If no active connection exists, you MUST initiate a new connection via COMPOSIO_MANAGE_CONNECTIONS with the correct toolkit name. DO NOT execute any toolkit tool without an ACTIVE connection.\n - Time Info: The response includes the current UTC time for reference. You can reference UTC time from the response if needed.\n - The tools returned to you through this are to be called via COMPOSIO_MULTI_EXECUTE_TOOL. Ensure each tool execution specifies the correct tool_slug and arguments exactly as defined by the tool's input schema.\n - The response includes a memory parameter containing relevant information about the use case and the known fields that can be used to determine the flow of execution. Any user preferences in memory must be adhered to.\n\nSESSION: ALWAYS set this parameter, first for any workflow. Pass session: {generate_id: true} for new workflows OR session: {id: \"EXISTING_ID\"} to continue. ALWAYS use the returned session_id in ALL subsequent meta tool calls.\n "
316
},
317
{
318
"slug": "COMPOSIO_WAIT_FOR_CONNECTION",
docs/public/openapi.json
+13
-2
@@ -891,6 +891,7 @@
891
"/api/v3/auth_configs": {
892
"post": {
893
"summary": "Create new authentication configuration",
894
+ "description": "Creates a new auth config for a toolkit, allowing you to use your own OAuth credentials or API keys instead of Composio-managed authentication. This is required when you want to use custom OAuth apps (bring your own client ID/secret) or configure specific authentication parameters for a toolkit.",
895
"tags": [
896
"Auth Configs"
897
],
@@ -1240,6 +1241,7 @@
1241
},
1242
"get": {
1243
"summary": "List authentication configurations with optional filters",
1244
+ "description": "Retrieves all auth configs for your project. Auth configs define how users authenticate with external services (OAuth, API keys, etc.). Use filters to find configs for specific toolkits or to distinguish between Composio-managed and custom configurations.",
1245
"tags": [
1246
"Auth Configs"
1247
],
@@ -2342,6 +2344,7 @@
2344
"/api/v3/connected_accounts": {
2345
"get": {
2346
"summary": "List connected accounts with optional filters",
2347
+ "description": "Retrieves all connected accounts for your project. Connected accounts represent authenticated user connections to external services (e.g., a user's Gmail account, Slack workspace). Filter by toolkit, status, user ID, or auth config to find specific connections.",
2348
"tags": [
2349
"Connected Accounts"
2350
],
@@ -9145,6 +9148,7 @@
9148
},
9149
"post": {
9150
"summary": "Create a new connected account",
9151
+ "description": "Initiates a new connection to an external service for a user. For OAuth-based toolkits, this returns a redirect URL to complete authentication. For API key-based toolkits, provide the credentials directly in the request body. Use the `user_id` field to associate the connection with a specific user in your system.",
9152
"tags": [
9153
"Connected Accounts"
9154
],
@@ -37335,8 +37339,7 @@
37339
"required": false,
37340
"description": "Optional version of the tool to retrieve",
37341
"name": "version",
37338
- "in": "query",
37339
- "deprecated": true
37342
+ "in": "query"
37343
},
37344
{
37345
"schema": {
@@ -40779,6 +40782,8 @@
40782
},
40783
"/api/v3/trigger_instances/{slug}/upsert": {
40784
"post": {
40785
+ "summary": "Create or update a trigger",
40786
+ "description": "Creates a new trigger instance or updates an existing one with the same configuration. Triggers listen for events from external services (webhooks or polling) and can invoke your workflows. If a matching trigger already exists and is disabled, it will be re-enabled. Requires a connected account ID to associate the trigger with a specific user connection.",
40787
"tags": [
40788
"Triggers"
40789
],
@@ -41008,6 +41013,8 @@
41013
},
41014
"/api/v3/trigger_instances/active": {
41015
"get": {
41016
+ "summary": "List active triggers",
41017
+ "description": "Retrieves all active trigger instances for your project. Triggers listen for events from connected accounts (e.g., new emails, Slack messages, GitHub commits) and can invoke webhooks or workflows. Use filters to find triggers for specific users, connected accounts, or trigger types.",
41018
"tags": [
41019
"Triggers"
41020
],
@@ -41404,6 +41411,8 @@
41411
},
41412
"/api/v3/trigger_instances/manage/{triggerId}": {
41413
"delete": {
41414
+ "summary": "Delete a trigger",
41415
+ "description": "Permanently deletes a trigger instance. This stops the trigger from listening for events and removes it from your project. Use the PATCH endpoint with status \"disable\" if you want to temporarily pause a trigger instead.",
41416
"tags": [
41417
"Triggers"
41418
],
@@ -41510,6 +41519,8 @@
41519
}
41520
},
41521
"patch": {
41522
+ "summary": "Enable or disable a trigger",
41523
+ "description": "Updates the status of a trigger instance to enable or disable it. Disabling a trigger pauses event listening without deleting the trigger configuration. Re-enabling restores the trigger to its active state. Use this for temporary maintenance or to control trigger execution.",
41524
"tags": [
41525
"Triggers"
41526
],