grasp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
grasp lets human reviewers see and judge your work as decisions, not just diffs. Before you change code for a non-trivial reason, call record_decision once per decision: what you decided, why, the files it touches, alternatives you rejected, and any risk. Small mechanical edits (typos, formatting) need no decision. After implementing a decision that changes what the software does, call show_behavior with a command that demonstrates it. grasp runs the command on the code from before your session and on the code now, and shows reviewers both real outputs, so they can see the change without reading code. Make the command print one short line per case, like "empty title -> 400 title is required" (for an HTTP API: start the server, send the requests with curl, print status and the key part of the body, stop the server). At the start of a task, call get_review_feedback and follow it.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_review_feedbackA | Get reviewer verdicts and comments on your earlier decisions. Rejected decisions and comments are instructions to follow. |
| record_decisionA | Record a decision before making the changes that carry it out, so reviewers can approve or reject it. Use one call per decision (architecture, data model, API, business rule, dependency, security, performance, testing, quality). |
| show_behaviorA | Show reviewers what a change does. grasp runs your command twice, on the code from before this session and on the code now, and shows both real outputs side by side. The command runs from the project root with sh; it must start and stop anything it needs and print a short result. Use one call per behavior you want to demonstrate. |
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 3 tools
Each tool occupies a distinct phase of the review loop: record_decision writes, show_behavior demonstrates evidence, get_review_feedback reads reviewer verdicts. No two tools could plausibly be selected for the same intent.
All three names follow a strict verb_noun snake_case pattern (get_review_feedback, record_decision, show_behavior). The verbs accurately signal direction (read/write/demonstrate).
Three tools is minimal but each maps to a necessary step in the submit-review-revise workflow, so nothing feels padded. It sits at the low end of the comfortable range, leaving little room for auxiliary operations.
The core loop (record decision, demonstrate behavior, collect feedback) is fully covered. Minor gaps exist around inspecting previously recorded decisions or withdrawing/amending one, but the workflow can proceed without those.