agentgrasp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@agentgrasprun npm test, then ask whether any failures are timeouts"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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
curl --proto '=https' --tlsv1.2 -LsSf https://github.com/damejeras/agentgrasp/releases/latest/download/agentgrasp-installer.sh | sh
claude plugin marketplace add damejeras/agentgrasp
claude plugin install agentgrasp@agentgraspInstead 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.
Related MCP server: distil
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:
{
"sandbox": {
"filesystem": {
"allowWrite": ["~/.local/state/agentgrasp"]
}
}
}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
This server cannot be deployed
Maintenance
Related MCP Connectors
Same functionality, consuming only 1/20 of the context window tokens.
Use your Mac, Windows or Linux computer from ChatGPT, Claude or Codex: files, commands, documents.
Share documents privately from an AI agent. The agent gets a link; it cannot read the file.
41Turn assistant output into ready-to-send action links and files, with no sign-in.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceCompresses file reads, command output, search hits, and fetched web pages before entering agent context to reduce token usage, using deterministic transforms and a safety verifier.6 npm9MIT
- AlicenseAqualityAmaintenanceReversibly compress a large tool output to a recoverable 8-hex handle over stdio, expand it back to the exact original bytes on demand, and report a local token/dollar savings ledger. Zero runtime dependencies; content never leaves the machine.3233 PyPI20Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables offloading large tool outputs from LLM context and recalling them on demand to save tokens.-
- AlicenseAqualityAmaintenanceEnables AI coding assistants to capture large command outputs into an ephemeral in-memory buffer and search them via hybrid BM25 and semantic retrieval with line-level context.194Apache 2.0