@alabasta/mcp
Gathers git diff, commits, PR state, and CI checks to enrich task resolutions.
Click on "Install 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., "@@alabasta/mcpRead task TOM-24 and start work"
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.
@alabasta/mcp
MCP server that connects coding agents (Claude Code, Codex, Cursor, …) to Alabasta tasks. The agent can read a task, start work, and submit a structured resolution — what changed, verification, what's unverified, deferred work, references — which a human reviews inside Alabasta.
It never overwrites the task description and never marks a task done: submitting a resolution moves the task to review, and only a human Accept reaches Done.
This is a thin stdio adapter over Alabasta's /agent/v1/* HTTP API. The API key
encodes the workspace and principal, so that plus the site URL is all the config
it needs.
Setup
In Alabasta, go to Workspace settings → Agent access and generate an API key (shown once).
Note your deployment's site URL — the
https://<deployment>.convex.sitevalue (NEXT_PUBLIC_CONVEX_SITE_URL).
Claude Code
claude mcp add alabasta \
--env ALABASTA_SITE_URL=https://<deployment>.convex.site \
--env ALABASTA_API_KEY=alab_sk_... \
-- npx -y @alabasta/mcpCodex / manual (.mcp.json)
{
"mcpServers": {
"alabasta": {
"command": "npx",
"args": ["-y", "@alabasta/mcp"],
"env": {
"ALABASTA_SITE_URL": "https://<deployment>.convex.site",
"ALABASTA_API_KEY": "alab_sk_..."
}
}
}
}Environment
Variable | Required | Purpose |
| yes |
|
| yes | Workspace API key ( |
| no | Default task for this session (a launcher can export it, so tools work without a |
| no | Correlates a resolution to an agent run (used as |
Related MCP server: agent-comm
Tools
Tool | Does |
| Read a task by |
| List tasks assigned to you, optional |
| Move a task to in progress |
| Gather real diff stat, commits, PR state, and CI checks (git + |
| Submit the structured resolution (→ in review) |
| Move a task to in review without a full resolution |
| Record why the task couldn't be completed |
Resolution submits are idempotent on (taskId, externalRunId, revision) — a
resubmit updates the same record; a new revision creates a new attempt.
CLI launcher
Bind a coding-agent session to a task in one command:
alabasta work TOM-24 --agent claude # or --agent codex
alabasta work TOM-24 --branch # also cut a branch: tom/TOM-24-<slug>
alabasta work TOM-24 --print # print the env + command instead of launchingIt fetches the task, mints a run id, exports ALABASTA_TASK_ID + ALABASTA_RUN_ID, and
launches the agent with a priming prompt — the installed plugin (skill + MCP + Stop hook)
takes it from there. --print is what the Alabasta UI's "Copy agent command" produces.
Needs ALABASTA_SITE_URL + ALABASTA_API_KEY in the environment.
Claude Code plugin (skill + enforcement)
claude-plugin/ bundles three layers so the feature is reliable, not just possible:
Hands —
.mcp.jsonwires the MCP server above (setALABASTA_SITE_URL+ALABASTA_API_KEYin your env).Training —
skills/task-resolution/SKILL.mdteaches the agent the resolution protocol, format, and invariants (preserve scope; separate verified from unverified; no conversational text).Enforcement —
hooks/stop.py(a Stop hook) blocks the agent from finishing when it edited code for a linked Alabasta task but never submitted a resolution. It nudges at most twice, then allows the stop, so it can never trap a session. Task linkage comes fromALABASTA_TASK_IDor a branch name containing an identifier (e.g.tom/TOM-24-fix).
Requires python3 (stdlib only). Install it via the bundled marketplace:
/plugin marketplace add cowboyshibuya/alabasta-agent-bridge # or a local path to this repo
/plugin install alabasta@alabastaThe marketplace catalog is .claude-plugin/marketplace.json at the repo root; the plugin
source is the self-contained claude-plugin/ directory. (Relative-path sources need a git or
local marketplace add, not a bare URL to the JSON file.) Alternatively, copy
hooks/hooks.json into your .claude/settings.json and the skill into .claude/skills/.
Develop
bun install # or npm install
npm run build # tsc -> dist/
node dist/index.jsRoadmap
Done: MCP server (hands), resolution skill (training), Stop-hook enforcement
(Claude Code and Codex — see codex/), the alabasta work CLI
launcher, Git/CI/PR enrichment (alabasta_collect_git_context), and the
marketplace-installable Claude Code plugin bundle. Next: a remote HTTP
transport (enabling per-user OAuth) and automated CI publishing — see
DEVELOPMENT.md.
Contributing / maintaining this repo
See DEVELOPMENT.md — what MCP is, how the pieces fit together, how to add a new tool, and how to publish a new version (including the exact failure modes hit the first time and how to avoid them).
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/cowboyshibuya/alabasta-agent-bride'
If you have feedback or need assistance with the MCP directory API, please join our Discord server