main.js · part 155

60 text occurrences from desktop/Cursor.app/Contents/Resources/app/extensions/cursor-agent-host/dist/main.js, part 155. Every entry preserves the shipped literal and its saved verdict or selection reason.

File contents and all parts · All files

When true, the tool's result is written to a file under agent-tools/ in the workspace instead of being returned inline, regardless of its size; the result then reports the file path, size, and line count. Use it when you expect a large result that you want to read selectively or pass on to another tool by path. System reminders attached to the call are still returned inline.

MCP-specific call metadata. Set this only when invoking a tool from an external MCP namespace; omit it for first-party tools in the cursor namespace.

Missing required ${1===e.length?"field":"fields"}: ${e.join(", ")}. Re-issue the call with the tool's identity set; `arguments` alone does not identify the tool.

Failed to parse arguments string as JSON object. Re-issue the call with `arguments` as a JSON object literal rather than a quoted string.

"description": "Search the public docs for the example API",
  

Set "write_to_file": true to have the result written to a file under agent-tools/ in the workspace instead of returned inline, regardless of its size; you then get back the file path, size, and line count. Prefer it for results you expect to be large and want to read selectively or hand to another tool by path.

For tools in external MCP namespaces (not the cursor namespace), any string argument, at any nesting depth, that is exactly "${Ne.Eyz}/absolute/path" is replaced with that file's contents when the call is sent, so a file (for example one produced by write_to_file) can be passed to the server without reading it into the conversation. Text files only, up to a few MiB; if the tool accepts a path, pass the plain path instead. Example: "arguments": { "body": "${Ne.Eyz}/workspace/agent-tools/1f3c.txt" }.

write_to_file could not write the tool result

${Buffer.byteLength(s,"utf8")>gu.g4?Au(s):s}

[write_to_file was requested but the result could not be written to a file; it is returned inline instead.]

Invoke one tool from a dynamic namespace, e.g. an MCP server. IMPORTANT: Always call ${t} for this namespace/tool before calling to ensure correct parameters. Set mcpDetails only for tools from external MCP namespaces; omit it for first-party tools in the cursor namespace.

Example:
{
  "namespace": "my-namespace",
  "toolName": "search",
  "mcpDetails": { "description": "Search the public docs for the example API" },
  "arguments": { "query": "example", "limit": 10 }
}${ue}

Call an MCP tool by server identifier and tool name with arbitrary JSON arguments. IMPORTANT: Always call ${t} for this server/tool before calling to ensure correct parameters.

Example:
{
  "server": "my-mcp-server",
  "toolName": "search",
  ${ce}"arguments": { "query": "example", "limit": 10 }
}${ue}

Call an MCP tool by server identifier and tool name with arbitrary JSON arguments. IMPORTANT: Always read the tool's schema/descriptor BEFORE calling to ensure correct parameters.

Example:
{
  "server": "my-mcp-server",
  "toolName": "search",
  ${ce}"arguments": { "query": "example", "limit": 10 }
}

MCP file system options are required for CallMcpTool

Interactive MCP authentication is only available in the Cursor desktop IDE.

Interactive MCP authentication is only available in the Cursor desktop IDE.

Interactive MCP authentication is not available in this agent environment. Ask the user to authenticate the MCP server in the Cursor desktop IDE, then retry.

"${a.server}" is a built-in Cursor server that does not use interactive authentication.

${e} If its tools are failing, the failure is not an authentication problem; read the tool error and address that instead.

Tool "${a.toolName}" on "${a.server}" is not available in this agent context.

${e} It speaks to the end user on the parent agent's behalf and is reserved for the parent agent. Include anything you want communicated in your final response instead.

Built-in tool dispatch via CallDynamicTool

No built-in tools are available ${U?"in namespace":"on server"} "${a.server}".

in namespace

on server

Built-in tool "${a.toolName}" not found ${U?"in namespace":"on server"} "${a.server}". Available tools: ${e.join(", ")}. Use ${$} to discover their schemas.

in namespace

on server

Dynamic tool execution failed

Use ${$} to discover available ${U?"namespaces":"servers"}.

Tool ${t} was not found. Use ${$} to discover available ${U?"namespaces":"servers"} and their tools.

MCP tool call

You called this tool without first discovering its schema via ${$}. For future calls, call ${$} with {"${U?"namespace":"server"}":"${a.server}","toolName":"${a.toolName}"} before calling ${r}.

You called this MCP tool without first reading its schema/descriptor file. For future calls to this tool, please read the tool definition at "${ee.unreadPath}" first to ensure you're using the correct parameters.

The ${U?"namespace":"MCP server"} rejected these arguments as invalid. Before retrying, call ${$} with {"${U?"namespace":"server"}":"${a.server}","toolName":"${a.toolName}"} and rebuild the arguments from the returned input schema.

MCP server

The MCP server rejected these arguments as invalid. Before retrying, read the tool definition at "${ne}" and rebuild the arguments from that schema.

The MCP server rejected these arguments as invalid. Before retrying, read the MCP server descriptor files for "${a.server}" and the tool definition for "${a.toolName}" so the arguments match the schema.

Missing serverIdentifier or toolCallId

User rejected MCP authentication

Successfully authenticated MCP server: ${e}. The server's tools should now be available.

this environment's tool executor does not support them

"${Ne.Eyz}" arguments can't be used here: ${i}. Read the file and pass its contents instead.

MCP allowlist precheck failed

Smart Mode preflight rejected the MCP call

MCP call released early: a user steer was admitted

Failed to cancel Smart Mode MCP approval request after steer release

Failed to cancel Smart Mode MCP approval request

Error in call_mcp_tool

Tool execution error

${(e/1024).toFixed(1)} KB

${e} bytes

Large output has been written to: ${t.outputLocation.filePath} (${n}, ${r} lines)

Unhandled content case: ${e.content.case}

Tool rejected: ${t.value.reason}

Tool rejected

Error: ${t.value.error}. ${t.value.readToolDefReminder}

Error: ${t.value.error}

Permission denied: ${t.value.error}

Unknown error

Unhandled result case: ${t}

Perform browser-based testing and web automation. This subagent can navigate web pages, interact with elements, fill forms, and take screenshots. Use this for testing web applications, verifying UI changes, or any browser-based tasks. Use this browser subagent when you need to either: (1) parallelize browser tasks alongside other work, or (2) execute a longer sequence of browser actions that benefit from dedicated context. For simple, single browser actions, you may use the browser tools directly. This subagent requires agent mode because browser MCP access is unavailable in readonly mode. This subagent_type is stateful; if a browserUse subagent already exists, the previously created subagent will be resumed if you reuse the Task tool with subagent_type set to browserUse.