Cursor Agent MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEBUG_CURSOR_MCP | No | Set to '1' to log spawn/exit diagnostics to stderr | |
| CURSOR_AGENT_PATH | No | Absolute path to the cursor-agent binary; falls back to PATH | |
| CURSOR_AGENT_FORCE | No | Set to 'true' or '1' to inject -f unless already present | |
| CURSOR_AGENT_MODEL | No | Default model (appended as -m <model> unless you already provided one) | |
| CURSOR_AGENT_TIMEOUT_MS | No | Hard runtime ceiling in milliseconds | 30000 |
| CURSOR_AGENT_ECHO_PROMPT | No | Set to '1' to prepend the effective prompt to the tool's result | |
| CURSOR_AGENT_IDLE_EXIT_MS | No | Idle-kill threshold in ms; '0' disables idle kill (recommended) | 0 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| cursor_agent_chatC | Chat with cursor-agent using a prompt and optional model/force/output_format. |
| cursor_agent_edit_fileC | Edit a file with an instruction. Prompt-based wrapper; no CLI subcommand required. |
| cursor_agent_analyze_filesC | Analyze one or more paths; optional prompt. Prompt-based wrapper. |
| cursor_agent_search_repoC | Search repository code with include/exclude patterns. Prompt-based wrapper. |
| cursor_agent_plan_taskC | Generate a plan for a goal with optional constraints. Prompt-based wrapper. |
| cursor_agent_rawC | Advanced: provide raw argv array to pass after common flags (e.g., ["search","--query","foo"]). |
| cursor_agent_runC | Run cursor-agent with a prompt and desired output format (legacy single-shot). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
The tools have overlapping purposes that could cause confusion, particularly between cursor_agent_chat and cursor_agent_run which both involve prompt-based interaction with cursor-agent. Additionally, cursor_agent_raw is described as 'advanced' but its functionality might overlap with other tools, creating ambiguity in tool selection for specific tasks.
All tool names follow a consistent snake_case pattern with the prefix 'cursor_agent_' followed by a verb_noun combination (e.g., analyze_files, chat, edit_file). This uniformity makes the tool set predictable and easy to parse, with no deviations in naming conventions.
With 7 tools, the count is reasonable for a server focused on cursor-agent interactions, covering analysis, chat, editing, planning, raw commands, running, and searching. It is slightly on the lower side but still well-scoped for its purpose, with each tool appearing to serve a distinct role in the workflow.
The tool set covers key operations for interacting with cursor-agent, including analysis, chat, file editing, task planning, raw command execution, running prompts, and repository search. Minor gaps might exist, such as lack of tools for managing agent settings or handling multi-step workflows, but core functionalities are adequately represented for the domain.