Skip to main content
Glama
talvinder

Carrot AI PM

by talvinder

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CARROT_PROJECT_ROOTYesThe root directory of the project for Carrot to analyze.

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}
prompts
{
  "listChanged": true
}
resources
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
setup_carrotD
add_routeD
grow_specD
grow_ui_specD
grow_db_specD
grow_cli_specD
run_testsD
format_codeD
search_codeD
commit_changesD
check_spec_complianceD

Prompts

Interactive templates invoked by user choice

NameDescription
review_diffReview a git diff and provide structured feedback
draft_prGenerate a pull request description based on a diff
explain_fileExplain a file's purpose and public API surface

Resources

Contextual data attached and managed by the client

NameDescription
vibe.yamlOpenAPI specification for the API
README.mdRepository documentation
Issue #9559carrot_core
Issue #9697[WIP] carrot_impl
Issue #736standard location for user binaries like ~/bin/, so installers don't write to oshrc/oilrc
Issue #9337[seraphis] async: add async framework
Issue #469argparse builtin: Replacement / enhancement for getopts
Issue #453use builtin: for "first word lookup"
Issue #848Run every kind of binary (coprocesses, containers, VMs, remote versions of them ...)
Issue #1085Introspection for everything
Issue #852interactive shell: notice about failed commands
Issue #750mechanism to build shell scripts into the binary

TDQS

D1.9/5.0

Scored across 11 tools

Disambiguation3/5

Most tool names are distinct, but the multiple 'grow_*_spec' tools (grow_spec, grow_cli_spec, grow_db_spec, grow_ui_spec) could overlap in purpose. Without descriptions, agents may struggle to choose the correct one. A few other tools like 'add_route' and 'format_code' seem unrelated, but overall ambiguity is moderate.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern in snake_case (e.g., add_route, check_spec_compliance, grow_cli_spec). There are no deviations or mixed conventions, making the naming predictable and easy to interpret.

Tool Count5/5

With 11 tools, the count is well within the ideal range of 3-15. Each tool appears to serve a distinct purpose related to spec management, code operations, and testing, justifying its presence.

Completeness3/5

The tool set covers spec growth, code formatting, testing, and compliance, but lacks read/list operations for specs and code. There are no tools for deleting or updating existing entities, which could lead to agent failures in workflows requiring retrieval or modification.

Maintenance

ActivityInactive
ResponsivenessNo issues