sprucelab 0.1.4.4

Agent-first surface for Sprucelab — typed CLI + MCP server over the same public HTTP API.

sprucelab

Agent-first surface for Sprucelab. One install ships a typed CLI and an MCP server — both wrapping the same public HTTP API. Drop in whichever transport your agent host speaks.

pip install sprucelab

Two transports, one package

sprucelab — typed CLI

For terminal-resident agents (Claude Code, Aider, anything that drives a shell) and humans at the prompt. Every command supports --json for machine-readable output; mutations support --dry-run where applicable.

sprucelab auth register --token <YOUR_KEY> --url https://www.sprucelab.io
sprucelab projects list --json
sprucelab files upload ./models/foo.ifc --project-id <uuid> --wait
sprucelab verify --model-id <uuid> --dry-run

Agents move through sprucelab faster than humans do — the rendering is for humans; agents read the JSON. Once an agent has worked out the right sequence of calls, the same commands run unattended from cron / GitHub Actions / Airflow without burning tokens — that's the whole point of headless-first. The AI budget stays reserved for actual reasoning work (claim extraction, type classification, verification), not for re-deriving the same script every run. See sprucelab --help for the full command tree.

sprucelab-mcp — MCP server over stdio

For host-resident agents (Claude Desktop, Cursor, Continue, …) that launch tools as subprocesses and call them as typed tool calls.

{
  "mcpServers": {
    "sprucelab": {
      "command": "sprucelab-mcp",
      "env": {
        "SPRUCELAB_API_URL": "https://www.sprucelab.io",
        "SPRUCELAB_API_TOKEN": "your-token-here"
      }
    }
  }
}

The MCP server is a thin wrapper over the same HTTP surface the CLI talks to — the one advertised at https://www.sprucelab.io/api/capabilities/. No custom protocol, no surprises. If a tool fails, the error body is the literal API response.

Auth

Read-only discovery (capabilities, agent_tools_manifest, EIR catalog, EIR presets) works without auth on either transport. Everything else needs a token.

Get one via the web app at https://www.sprucelab.io/agents, then either:

sprucelab auth register --token <YOUR_KEY> --url https://www.sprucelab.io

…or set SPRUCELAB_API_TOKEN in the MCP env block above. The CLI and the MCP server read the same token store.

For experimentation, the public sandbox token (read-only) is published on https://www.sprucelab.io/agents.

MCP tools

Read-only discovery (no auth):

Tool	Purpose
capabilities()	Fetch the full capabilities manifest. Always start here.
agent_tools_manifest()	Fetch /.well-known/agent-tools.json.
eir_catalog()	EIR rule grammar — every kind, fields, singleton flag.
eir_presets(preset?)	Ready-to-seed EIR bundles.

Projects + EIR (Bearer):

Tool	Purpose
list_projects(), show_project(id)	Project listing + detail.
scaffold_project(name, …)	Create project + seed EIR in one call.
list_members(id), add_member(id, email, role), remove_member(id, member_id)	Per-project membership.
mint_tenant_token(id, name, scope), list_tenant_tokens(id), revoke_tenant_token(id, token_id)	Project-scoped agent tokens.
eir_rules(id)	List the active EIR config's rules.
eir_apply_preset(id, preset, mode)	Apply preset in merge or replace mode.
eir_add_rule(id, kind, config, upsert)	Append one rule; singleton 409 unless upsert=True.
eir_remove_rule(id, rule_id)	Idempotent rule delete.
eir_set_rules(id, rules)	Atomic full replace.

Models + types + verification (Bearer):

Tool	Purpose
list_models(project_id?)	List models in a project.
list_types(model_id), classify_types(mappings)	Type list + batch classify.
verify_dry_run(model_id), verify_model(model_id)	Verification, with persistence opt-in.

Files (Bearer):

Tool	Purpose
list_files(project_id?), show_file(id)	List + detail.
upload_file(project_id, file_path, on_duplicate)	Multipart upload from a local path.
reprocess_file(id)	Trigger a fresh ExtractionRun.
extraction_log(file_id, run_id?)	Full ExtractionRun (log_entries + quality_report).
list_observations(project_id?)	Layer-1 observation log.

Issues + scopes (Bearer):

Tool	Purpose
list_issues(…), show_issue(id), create_issue(…), update_issue(…), resolve_issue(id)	Issue CRUD.
issues_from_verification(model_id)	Route verification failures into issues.
list_scopes(project_id, as_tree), create_scope(…)	Federation scopes.

Webhooks (Bearer):

Tool	Purpose
list_webhooks(project_id?)	List subscriptions.
create_webhook(project_id, target_url, events)	Subscribe + receive signing secret ONCE.
disable_webhook(id, enable?)	Toggle is_active.
delete_webhook(id)	Permanent delete.
list_deliveries(id), redeliver(delivery_id), test_webhook(id)	Delivery log + replay + synthetic test.

Local-dev surface (sprucelab dev …)

The CLI also ships a dev subcommand that bypasses the API and talks directly to a local Django install — for working on Sprucelab, not against prod. Same agent-first invariants (--json everywhere, --dry-run on mutations).

sprucelab dev env                                        # repo + service status
sprucelab dev db stats --json                            # row counts for key tables
sprucelab dev db materials --project <uuid> --top 15     # top materials per project
sprucelab dev seed materials --project <uuid> --dry-run  # preview seed plan
sprucelab dev test tsc                                   # frontend type-check
sprucelab dev test e2e materials --headed                # Playwright smoke

Powered by

Sprucelab's IFC extraction layer is powered by ifcfast — 25–47× faster than ifcopenshell on production IFCs. See https://www.sprucelab.io/benchmarks.