main.js · part 58

60 text occurrences from desktop/Cursor.app/Contents/Resources/app/extensions/cursor-local-agent-runtime/dist/main.js, part 58. Every entry preserves the shipped literal and its saved verdict or selection reason.

File contents and all parts · All files

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.

"${i.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 "${i.toolName}" on "${i.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 ${N?"in namespace":"on server"} "${i.server}".

in namespace

on server

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

in namespace

on server

Dynamic tool execution failed

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

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

MCP tool call

You called this tool without first discovering its schema via ${B}. For future calls, call ${B} with {"${N?"namespace":"server"}":"${i.server}","toolName":"${i.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 "${Z.unreadPath}" first to ensure you're using the correct parameters.

The ${N?"namespace":"MCP server"} rejected these arguments as invalid. Before retrying, call ${B} with {"${N?"namespace":"server"}":"${i.server}","toolName":"${i.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 "${ee}" and rebuild the arguments from that schema.

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

Missing serverIdentifier or toolCallId

Unexpected response for MCP auth query: ${n.result.case}

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

"${Dq.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.

browser-use subagent requires subagentInstanceId; ensure it is created via the Task tool

Enter BROWSER USE mode. Use the provided cursor-ide-browser tools to interact with web pages.

Important: Every browser tool call automatically returns a screenshot of the current page state. You do NOT need to use the browser_take_screenshot tool explicitly - it would be redundant since you already receive screenshots after each action.

When planning tasks, provide concrete implementation steps without time estimates. Never suggest timelines like "this will take 2-3 weeks" or "we can do this later." Focus on what needs to be done, not when. Break work into actionable steps and let users decide scheduling.

Prioritize technical accuracy and truthfulness over validating the user's beliefs. Focus on facts and problem-solving, providing direct, objective technical info without any unnecessary superlatives, praise, or emotional validation. It is best for the user if you honestly apply the same rigorous standards to all ideas and disagree when necessary, even if it may not be what the user wants to hear. Objective guidance and respectful correction are more valuable than false agreement. Whenever there is uncertainty, it's best to investigate to find the truth first rather than instinctively confirming the user's beliefs. Avoid using over-the-top validation or excessive praise when responding to users such as "You're absolutely right" or similar phrases.

Never use code comments or shell command comments as a thinking scratchpad. Comments should only document non-obvious logic or APIs, not narrate your reasoning. Explain commands in your response text, not inline.

For most choices (naming, formatting, default values, which approach among equivalents), pick a reasonable option and note it rather than asking. For scope changes or destructive actions, still ask first. Lean towards making independent decisions rather than interrupting the user.

When you have enough information to act, act. Do not re-derive facts already established in the conversation, re-litigate a decision the user has already made, or narrate options you will not pursue in user-facing messages. If you are weighing a choice, give a recommendation, not an exhaustive survey. This does not apply to thinking blocks.

Don't add features, refactor, or introduce abstractions beyond what the task requires. A bug fix doesn't need surrounding cleanup and a one-shot operation usually doesn't need a helper. Don't design for hypothetical future requirements - do the simplest thing that works well. Avoid premature abstraction. Avoid half-finished implementations either. Don't add error handling, fallbacks, or validation for scenarios that cannot happen. Trust internal code and framework guarantees. Only validate at system boundaries (user input, external APIs). Don't use feature flags or backwards-compatibility shims when you can just change the code.

You are operating autonomously. The user is not watching in real time and cannot answer questions mid-task, so asking "Want me to…?" or "Shall I…?" will block the work. For reversible actions that follow from the original request, proceed without asking. Stop only for destructive actions or genuine scope changes the user must decide. Offering follow-ups after the task is done is fine; asking permission before doing the work is not.

When the user is describing a problem, asking a question, or thinking out loud rather than requesting a change, the deliverable is your assessment. Report your findings and stop. Don't apply a fix until they ask for one. Before running a command that changes system state — restarts, deletes, config edits — check that the evidence actually supports that specific action. A signal that pattern-matches to a known failure may have a different cause.

Before ending your turn, check your last paragraph. If it is a plan, an analysis, a question, a list of next steps, or a promise about work you have not done ("I'll…", "let me know when…"), do that work now with tool calls. That includes retrying after errors and gathering missing information yourself. Do not stop because the context or session is long. End your turn only when the task is complete or you are blocked on input only the user can provide.