From agami-core
Wires a local agami MCP server into Claude Desktop for database queries. Auto-detects Python, installs agami-core, and configures the desktop app.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agami-core:agami-serveWhen to use
Use when the user says 'set up agami for Claude Desktop', 'use agami in the Claude app', 'hook up the MCP server', 'let me test what my end users would see', '/agami-serve', or otherwise wants agami available outside Claude Code. Requires agami-connect to have run first (needs credentials + a semantic model). NOT needed to use agami inside Claude Code — the skills already work there.
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are setting up the local agami **MCP server** so the user can query their
You are setting up the local agami MCP server so the user can query their
database from the Claude Desktop app (or any client that reads a
claude_desktop_config.json-style file). This is the local mirror of the hosted
"Ask Agami" connector: same tool surface (list_datasources,
get_datasource_schema, get_prompt_examples, execute_sql),
but backed by the user's local model + local execution. Everything stays on the
machine; the server is stdio-only, has no auth, and makes no network call.
The heavy lifting is done by a deterministic helper —
scripts/setup_desktop_mcp.py. This skill's
job is to run it, read its output, and handle the two things that need a human:
a missing DB driver, and the app restart.
Run the detection + ask logic from shared/plan-mode-check.md. This skill needs Bash (to run the helper, which writes files). If plan mode is active, refuse with: "I can't wire up Claude Desktop in plan mode — it installs the agami-core package and writes your desktop config. Switch to Auto or Edit Automatically mode (Shift+Tab to cycle) and re-invoke me." DO NOT write a plan file. DO NOT call ExitPlanMode.
<artifacts_dir>/local/credentials must exist for the active profile. If missing, invoke /agami-connect first; the server needs a connection to execute against.<artifacts_dir>/<profile>/org.yaml must exist (so the server has a semantic model to serve). If not, invoke /agami-connect.$ARGUMENTS names a profile, pass it through as --profile <name>.Show the plan first with --dry-run, then do it for real:
# 1. Preview (writes nothing)
python3 "$AGAMI_PLUGIN_ROOT/scripts/setup_desktop_mcp.py" --dry-run
# 2. Apply
python3 "$AGAMI_PLUGIN_ROOT/scripts/setup_desktop_mcp.py"
Pass --profile <name> if the user named one. (Installation goes through sm install,
which does an editable install automatically when run from a dev checkout — no flag needed.)
pip install ... line, offer to run
it, then re-run the helper. Example: python3 -m pip install psycopg2-binary.list_datasources and return their profiles.~/Library/Logs/Claude/mcp-server-agami.log.Close with: this is the same toolset their business end-users would use through
the hosted Agami connector — the only difference is the backend (their local
files vs a shared, governed, always-on cloud). So what they just felt in Claude
Desktop is the end-user experience. If they want it for a team (one shared
model, evals, governance, reachable from web/mobile/Cowork), that's the hosted
product — see docs/open-vs-hosted.md in the repo
(https://github.com/AgamiAI/agami-core/blob/main/docs/open-vs-hosted.md).
agami entry in place and
re-installs the agami-core package. Re-run after a plugin update to refresh it..bak-<epoch> file.docs/privacy.md in the repo).npx claudepluginhub agamiai/agami-core --plugin agami-coreGenerates dbt MCP server config JSON, resolves authentication, and validates connectivity for Claude Desktop, Claude Code, Cursor, or VS Code.
Prepares a self-hosted deploy bundle for the multi-user agami MCP server, writing docker-compose.yml, Caddyfile, and agami.env, then runs or prints VM steps.
Guides developers through designing and building an MCP server for Claude, covering deployment model selection, tool-design patterns, and integration decisions.