
agentgrasp
io.github.damejerasv0.1.0Updated Oct 1, 2026
Yes/no questions about local files, and relevant-file search, with TypeSafe Jev
Overview
Keeps long Bash output out of a coding agent's context by saving it to files, with yes/no questions and relevant-file search over those files.
- What it does
- agentgrasp wraps each Bash command so long output is written to files instead of the agent's context, and the agent sees a short summary with the file path. The ask tool answers yes/no questions about a file, and the search tool returns relevant files and line ranges without returning source text. Both tools use Jev, TypeSafe's yes/no model.
- When to use it
- Useful when a coding agent runs commands that produce very long output and you want to keep the context small while still being able to query that output. It fits Claude Code workflows where you want to ask targeted yes/no questions or locate relevant files rather than read whole logs.
- Requirements
- Runs as a local process, installed via the installer script, npm install -g agentgrasp, or npx agentgrasp mcp. The TYPESAFE_API_KEY environment variable must be set in the environment that starts Claude Code; without it, ask and search return provider_unavailable. The Claude Code sandbox must allow writing to the agentgrasp state directory.
Installation
In SourceWeft
- Open agentgrasp 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
agentgrasp
agentgrasp keeps long command output out of a Claude Code agent's context. Claude Code still
runs every Bash command. When the output is long, agentgrasp saves it to a file and the agent
sees a short summary with the file path. The agent can then read the file, or ask yes/no
questions about it with the ask tool. The search tool finds the files and line ranges that
are relevant to a question, without returning source text.
ask and search use Jev, TypeSafe's yes/no model.
Install
Instead of the installer, npm install -g agentgrasp installs the same binary, and
npx agentgrasp mcp runs the MCP server without a global install.
The plugin calls agentgrasp from PATH. Set TYPESAFE_API_KEY in the environment that
starts Claude Code; without it, ask and search return provider_unavailable.
Settings
agentgrasp runs each Bash command inside a { ... } group that sends its output to files.
Claude Code asks for approval of every command that holds such a group, also when your allow
rules allow the command, and no allow rule changes that. So in Claude Code's default and
acceptEdits permission modes, every Bash call asks for approval. In bypassPermissions mode
the calls run without a prompt. Your deny rules still block a command in every mode.
When the Claude Code sandbox is on, let Bash write the agentgrasp state directory. Without this, the output cannot go to its files, the shell prints the error, and the command does not run:
Use $XDG_STATE_HOME/agentgrasp instead when XDG_STATE_HOME is set.
Costs and risks
askandsearchsend file content to TypeSafe. TypeSafe lists Jev at $42 per billion input tokens. Each call writes the tokens it used to its record under~/.local/state/agentgrasp/asks/orsearches/.askandsearchcan read any file inside the MCP roots, which are the project directory and the directories you add. This includes files that yourReaddeny rules block. When you allow these tools, you allow that.- The state directory grows until you delete files from it. agentgrasp never deletes them.
- A runaway command can fill the disk until Claude Code's timeout stops it.
Links
- MCP Registry name:
mcp-name: io.github.damejeras/agentgrasp
Source: README.md at commit f979585
Tools
0Version history
1- v0.1.0LatestOct 1, 2026

