agent-godmode
Gives you read_file, write_file, edit_file, run_command, and list_files operations scoped to a workspace directory, designed for building Cursor-style agents. Everything runs sandboxed to a root path you specify via AGENT_GODMODE_ROOT. The edit_file tool enforces exact search-and-replace matches to prevent drift. Commands run from argv arrays only, no shell injection surface. Ships with versioned system prompts and OpenAI tool definitions so you can wire up any LLM without rewriting schemas. Use it over MCP stdio in Cursor or call AgentWorkspace directly in Python. The package handles execution and sandboxing but brings no model or API keys. Fork of mcp-agent-tools with a namespace change.
- tools
- 5
- transport
- STDIO
- env var
- 1
- last updated
- Apr 27, 2026
Tools
5 toolsPublic tool metadata for what this MCP can expose to an agent.
read_fileRead a UTF-8 text file; optional line range and byte cap.
Read a UTF-8 text file; optional line range and byte cap.
No parameter schema in public metadata yet.
write_fileCreate or overwrite/append UTF-8 text; creates parent directories.
Create or overwrite/append UTF-8 text; creates parent directories.
No parameter schema in public metadata yet.
edit_fileSearch-and-replace in an existing UTF-8 file: non-empty old_string, optional replace_all.
Search-and-replace in an existing UTF-8 file: non-empty old_string, optional replace_all.
No parameter schema in public metadata yet.
list_filesList directory entries with optional recursion, glob, depth cap, dotfile control.
List directory entries with optional recursion, glob, depth cap, dotfile control.
No parameter schema in public metadata yet.
run_commandRun a subprocess from an argv list only (no shell); optional cwd under the root.
Run a subprocess from an argv list only (no shell); optional cwd under the root.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
AGENT_GODMODE_ROOTAbsolute workspace root; only paths under this directory are allowed. Omit if you pass --root to the CLI.
Readme
agent-godmode
Workspace-scoped MCP tools for building Cursor-style agents: read_file, write_file, edit_file, run_command, list_files. Includes strict, versioned system prompts (SYSTEM_PROMPT_V1) and OpenAI-style tool definitions so your app can wire any LLM with one import.
The LLM and API keys stay in your app. This package provides tool execution, sandboxing, and prompts—not a hosted model.
OpenAI + in-process tools: the Tier B section below is self-contained—copy the Python into a script, module, or REPL; no separate artifact is required.
Install
pip install agent-godmode
Editable / dev:
pip install -e ".[dev]"
Migrating from mcp-agent-tools: uninstall the old package, install agent-godmode, change Python imports from mcp_agent_tools to agent_godmode, the CLI from mcp-agent-tools to agent-godmode, and environment variables from MCP_AGENT_TOOLS_* to AGENT_GODMODE_* (for example AGENT_GODMODE_ROOT).
Tools
Details
- Repository
- github.com/mdvohra/agent-godmode
- Category
- AI & LLM Tools
- Package
agent-godmode- Transport
- STDIO
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
llm-oracleweiseer/llm-oracleUp-to-date LLM pricing + availability catalog with cited sources for AI agent routing.0stars
Agent-Native Analyticsbuilderio/agent-nativeAgent-Native Amplitude/Mixpanel - connect data sources, prompt for charts7.6KstarsAgent-Native Dispatchbuilderio/agent-nativeCentral Slack/Telegram router with jobs, memory, approvals, and A2A delegation7.6Kstars
GPT Researcherassafelovic/gptr-mcpMCP server for enabling LLM applications to perform deep research via the MCP protocol346stars
RAG Documentationhannesrudolph/mcp-ragdocsAn MCP server implementation that provides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their resp261stars
Agent Commsexadev/agent-commsCross-harness communication mesh for LLM agents — rooms, DMs, presence, and visibility over TCP37stars