Skip to main content

MCP server wrapping the Smalt's storage surface (read/write/link/claim/search) for ParkviewLab's CoGrind project.

Project description

smalt-mcp

MCP server wrapping the Smalt's storage surface (read / write / link / claim / search) for ParkviewLab's CoGrind project. Thinnest viable wrapper around markdown + LanceDB; no agentic logic. Single-writer to a given Smalt.

To cobalt-grinding what deco-assaying is to tree-sitter: a clean MCP-shaped wrapper around a deterministic capability.

Status

v0 foundation. Server runs; one MCP tool (status) wired up; storage layer ported from cobgrind/storage/ and ready for the rest of the tool surface. Track A of CoGrind's M2.7 plan — see cobalt-grinding/docs/plan.md for the full design.

Coming in the next iterations: read-only tools (list_pages, read_page, search, traverse, list_domains, list_proposals), read-write tools (write_page, write_pages, add_link, add_claim, write_proposal, bootstrap), auto-indexer-trigger on writes, end-to-end integration with CoGrind.

Run

Same five-mode pattern as deco-assaying. Pick whichever fits.

Mode When to use
1. uvx (one-off) Try it once, no install.
2. uv tool install (pinned daemon) Run it occasionally, want it on $PATH.
3. macOS LaunchAgent Persistent daemon on a Mac.
4. Linux systemd user unit Persistent daemon on Linux.
5. Docker / docker compose Container deployment.

In every mode the server listens on PORT (default 35833). Sanity-check:

curl http://127.0.0.1:35833/health

From source (current; until first release)

git clone https://github.com/ParkviewLab/smalt-mcp.git
cd smalt-mcp
uv sync
SMALT_DIR=~/Documents/Smalt uv run python -m smalt_mcp

Docker (after first release)

docker pull ghcr.io/parkviewlab/smalt-mcp:latest
docker run --rm \
  -p 35833:35833 \
  -e SMALT_SCOPE=read_only \
  -v smalt-data:/data \
  ghcr.io/parkviewlab/smalt-mcp:latest

Or use docker-compose.yml.

Endpoints

  • POST /sse — MCP Streamable HTTP transport. Tools.
  • GET /health — liveness probe ({ok, version, uptime_seconds}).
  • GET /admin/version — server identity + scope + configured Smalt path.
  • GET /docs — OpenAPI / Swagger UI for the HTTP routes.

HTTP responses are gzipped when the client sends Accept-Encoding: gzip.

MCP tools (v0)

Read-only:

  • status — Smalt path, existence, LanceDB tables present, page count, single-writer mutex state, embedding provider. Always safe to call.

Read-write: (coming next iteration)

The full target surface is in cobalt-grinding/docs/plan.md under "Track A — ParkviewLab/smalt-mcp v0".

Configuration

Env var Default Purpose
PORT 35833 HTTP listen port.
HOST 0.0.0.0 HTTP bind address.
SMALT_DIR ~/Documents/Smalt Path to the Smalt this server wraps. Auto-created on bootstrap (planned).
SMALT_SCOPE read_write read_only or read_write. Read-only deployments only expose tools that don't mutate the corpus.
EMBEDDING_PROVIDER fastembed Embedding backend. fastembed is the only one wired up; voyage / openai are placeholders.
EMBEDDING_MODEL BAAI/bge-small-en-v1.5 Model name passed to the provider.
EMBEDDING_DIM 384 Must match the model.
SMALT_INTERNAL_TOKEN (unset) Reserved for future per-client scope routing; not yet enforced.

Releasing

Tag-driven via the release workflow on push of a v* tag. Use the ParkviewLab/dev-tools helpers — they enforce the SSOT-tag-CI loop (pyproject.toml is the only place the version lives; CI verifies the pushed tag matches before publishing).

git bump patch              # 0.1.5 → 0.1.6, committed
git release                 # annotated tag v0.1.6 from pyproject.toml
git push --follow-tags      # CI fires

Don't have the helpers? Install once: git clone https://github.com/ParkviewLab/dev-tools.git ~/dev-tools && cd ~/dev-tools && ./install.sh.

License

MIT. See LICENSE.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

smalt_mcp-0.1.0.tar.gz (123.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

smalt_mcp-0.1.0-py3-none-any.whl (41.3 kB view details)

Uploaded Python 3

File details

Details for the file smalt_mcp-0.1.0.tar.gz.

File metadata

  • Download URL: smalt_mcp-0.1.0.tar.gz
  • Upload date:
  • Size: 123.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for smalt_mcp-0.1.0.tar.gz
Algorithm Hash digest
SHA256 d1662c474bc6bf071c985725f2bfcae18ce250bfee1493c2cde59fa61a852358
MD5 376a4cd48bb6018e1a2f6b8db04f126e
BLAKE2b-256 5af2a6c798f1a09d0c1c0110286c62e7747933750b9486cf4239e820d9220839

See more details on using hashes here.

Provenance

The following attestation bundles were made for smalt_mcp-0.1.0.tar.gz:

Publisher: release.yml on ParkviewLab/smalt-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file smalt_mcp-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: smalt_mcp-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 41.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for smalt_mcp-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 c4a07b89ceb160eca9ec21a8f36a6df6c75d82cbde9f31ae35be02dfe33cdcb6
MD5 323c15dccbf3da1581b0886a3486fbe0
BLAKE2b-256 a0a34b7d7ce4b27d118559766e3dee6b7222bd67a7acaeea8d60e7ec27c27600

See more details on using hashes here.

Provenance

The following attestation bundles were made for smalt_mcp-0.1.0-py3-none-any.whl:

Publisher: release.yml on ParkviewLab/smalt-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page