
Mcp Aider Executor
io.github.RailKillPublished by GitHub account RailKillv1.1.0Updated Oct 24, 2026
Model Context Protocol (MCP) server to execute aider-specific code editing operations
Overview
Runs aider as a detached background process so an assistant can start code-editing jobs and later check their progress.
- What you can do
- This stdio MCP server launches aider in the background with a given message prompt and records the process ID, start time, and original prompt in files next to the project. It exposes tools to check whether the process is still running and to read the aider chat history for progress, plus basic git tools (log, status, branches, checkout, stash, revert) and file tools (list files, read file contents, read and create .aider.conf.yml). A whitelist of glob paths controls which directories operations may touch.
- When to use it
- Use it when you want an assistant to kick off aider code-editing runs in a project and poll them later, for example to coordinate several background editing agents. It suits local, desktop development workflows where aider is already part of your toolchain.
- Requirements
- Runs locally over stdio, typically via npx, so Node.js is needed, and the shell must also have aider and git available as executable commands. Aider model settings and API credentials are supplied through environment variables such as AIDER_MODEL, OPENAI_API_BASE, and OPENAI_API_KEY. At least one --whitelist glob path must be passed, otherwise all operations are denied by default.
Installation
In SourceWeft
- Open Mcp Aider Executor in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
Project Information
stdio MCP server to run aider as a detached background process
with basic git tools and status checks. This allows LLMs to start code editing processes
freely and check the aider chat history for progress at a later time to allow for agentic swarm behavior.
An .aider.mcp.details.json file is created in the same directory with the process ID and starting datetime.
The MCP server provides tools for LLM agents to check if the process is still running,
and to check the .aider.chat.history.md for updates.
The original message prompt send via the MCP server to aider is also recorded in .aider.mcp.prompt.txt.
Quick Start
You can run the server directly using npx, passing in environment variables for the endpoint URL and API keys.
Provide --whitelist arguments with a permitted glob path otherwise all operations will be denied by default.
Prompting
You can directly tell your LLM to use Aider by providing them with a directory to work in. For example:
For extra Aider options, you should set it properly using environment variables (the env in MCP settings .json),
or ask your LLM to create the Aider YAML configuration file for you in the project directory. By default, the
server comes with some basic git and file tools to allow the LLM to look around. These tools can be disabled via
the options below if you'd like to use a separate MCP server to handle more advanced functions.
[!CAUTION]
For security purposes, the MCP server does not have the functionality to write API keys into the configuration YAML. Use
envinstead to provide keys likeOPENAI_API_KEY. Don't tell your LLM about it.
Options
You can add these arguments in the npx command.
Environment Prerequisites
The environment running the MCP server must have the following tools installed and available as executable commands in the shell:
- node
- aider
- git
[!WARNING]
You should set the number of parallel requests to 2 if you are using the same local endpoint for
aider, otherwise your chat session and the backgroundaiderprocess will be stuck waiting for each other.You should also set the
OPENAI_API_KEYenvironment variable to a non-empty value if you are using a local OpenAI-compatible endpoint becauseaiderrequires it even if you don't use an API key.You still need the
openai/prefix when specifying model names for local endpoints inaider.
Available MCP Tools
These are the list of MCP tools available for your LLM to call.
aider_check_git_log: Checks recent commits.aider_check_git_status: Callsgit status --shortto check the state of the given directory.aider_check_last_prompt: Returns the original prompt message of the last Aider run.aider_check_progress: Checks the Aider chat history and background process status.aider_checkout_git_branch: Switches git branches, creating a new one if it doesn't exist.aider_create_git_stash: Stashes everything to clear the directory for Aider (git stash -u).aider_git_revert: Reverts changes from a git commit by its hash.aider_list_files: Lists all files in a given directory.aider_list_git_branches: Returns a list of git branches in the given directory.aider_mcp_check_whitelist: Checks what glob paths are whitelisted for this Aider MCP server.aider_message_prompt: Startsaideras a background process with a given message prompt.aider_read_config_yaml: Returns the full content of the .aider.conf.yml in the directory.aider_read_file_contents: Reads the contents of a given filepath.aider_setup_config_yaml: Creates the .aider.conf.yml file in the directory.
Source: README.md at commit ba64d85
Tools
0Version history
1- v1.1.0LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts