Skip to content

docs: add Docker MCP Toolkit + SQLite MCP runbook#620

Open
chronicgiardia wants to merge 1 commit into
Graphify-Labs:v5from
chronicgiardia:docs/docker-mcp-sqlite
Open

docs: add Docker MCP Toolkit + SQLite MCP runbook#620
chronicgiardia wants to merge 1 commit into
Graphify-Labs:v5from
chronicgiardia:docs/docker-mcp-sqlite

Conversation

@chronicgiardia

Copy link
Copy Markdown
Contributor

Summary

Adds docs/docker-mcp-sqlite.md, a reproducible runbook for installing the SQLite MCP server into Docker MCP Toolkit. Once installed, any connected MCP client (Claude Code, Cursor, VS Code, etc.) gains six SQLite tools — read_query, write_query, create_table, list_tables, describe_table, append_insight — alongside graphify's knowledge-graph tools.

The doc is optional and unrelated to graphify's pipeline. Linked from README.md under a new "Optional integrations" section so it's discoverable without cluttering the main docs.

Why

Many graphify users already run Docker Desktop and use AI clients with MCP. Pairing a lightweight, persistent SQL workspace with the knowledge graph is a natural fit and a common request.

Notes for reviewers

  • The runbook documents a real catalog gotcha: the catalog ships two SQLite images. mcp/sqlite-mcp-server has a broken entrypoint (/app/.venv/bin/mcp-server-sqlite does not exist in the published layer); mcp/sqlite (marked "Archived" but functional) is recommended. The doc explains both and points at the working one.
  • Verified end-to-end: image MCP handshake → docker mcp profile server add → all 6 tools callable via docker mcp tools call → data persists across container invocations on the mcp-sqlite named volume.
  • Branched from upstream/v5; does not include Fix invalid escape sequence SyntaxWarning in __main__.py #602's escape-sequence fix and does not conflict with it.

Files

  • docs/docker-mcp-sqlite.md (new, ~140 lines)
  • README.md (small "Optional integrations" section + table row)

Co-Authored-By: Oz oz-agent@warp.dev

Adds docs/docker-mcp-sqlite.md, a reproducible recipe for installing the
SQLite MCP server into Docker MCP Toolkit so any connected MCP client
(Claude Code, Cursor, VS Code, etc.) gains six SQLite tools alongside
graphify's knowledge-graph tools.

Notes the catalog has two SQLite images at time of writing: `mcp/sqlite`
(marked Archived but works) and `mcp/sqlite-mcp-server` (broken
entrypoint). Recommends the working one.

Linked from README.md under a new 'Optional integrations' section.

This is unrelated to the upstream graphify pipeline; it lives as an
optional companion runbook for users who want a lightweight persistent
SQL workspace exposed to their MCP-aware AI clients.

Co-Authored-By: Oz <oz-agent@warp.dev>
Copilot AI review requested due to automatic review settings April 30, 2026 05:02

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Adds an optional documentation runbook describing how to set up the Docker MCP Toolkit with a SQLite MCP server, and links it from the main README so users can discover it without impacting graphify’s core pipeline/docs.

Changes:

  • Added a new runbook: docs/docker-mcp-sqlite.md covering install, smoke tests, persistence, client wiring, uninstall, and troubleshooting.
  • Linked the new runbook from README.md under a new “Optional integrations” section.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

File Description
docs/docker-mcp-sqlite.md New end-to-end setup/runbook for Docker MCP Toolkit + SQLite MCP server, including troubleshooting and persistence notes.
README.md Adds an “Optional integrations” section with a link to the new runbook.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment thread docs/docker-mcp-sqlite.md
docker mcp tools call read_query \
query='SELECT * FROM notes ORDER BY id'
docker mcp tools call describe_table table_name=notes
docker mcp tools call append_insight insight='3 rows inserted; aggregates work.'

Copilot AI Apr 30, 2026

Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The example append_insight text says "3 rows inserted" but the preceding INSERT statement inserts 2 rows. This makes the smoke test internally inconsistent; update the insight text or the insert statement so they match.

Suggested change
docker mcp tools call append_insight insight='3 rows inserted; aggregates work.'
docker mcp tools call append_insight insight='2 rows inserted; aggregates work.'

Copilot uses AI. Check for mistakes.
Comment thread docs/docker-mcp-sqlite.md
The Docker MCP gateway should now expose 6 additional tools:
```bash
docker mcp tools count
# → 15 tools (was 9 before adding SQLite)

Copilot AI Apr 30, 2026

Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

docker mcp tools count output is installation/profile dependent; hard-coding "15 tools (was 9)" may be incorrect for users with other servers enabled or different Docker versions. Consider stating that the count should increase by 6 after adding SQLite, or show how to list tool names instead of relying on a specific total.

Suggested change
# → 15 tools (was 9 before adding SQLite)
# The total is installation/profile dependent; it should be 6 higher than before adding SQLite.

Copilot uses AI. Check for mistakes.
safishamsi pushed a commit that referenced this pull request May 2, 2026
Adds docs/colabfold-macos-install.md, a reproducible recipe for
installing LocalColabFold (ColabFold + AlphaFold2 weights) on Apple
Silicon Macs, so users can predict protein structures locally and feed
the resulting PDBs / confidence scores into a graphify corpus.

Notes upstream LocalColabFold's current top-level installer hardcodes
Linux x86_64 Miniforge and jax[cuda12], which fail on Apple Silicon (no
macOS CUDA wheels, no NVIDIA GPU). Recommends the bundled v1.5.5 M1
installer as the working Apple Silicon path. ColabFold 1.6.1 with
JAX 0.4.23 CPU build, verified by 60s smoke test on a 62-residue FASTA.

Linked from README.md under the existing 'Optional integrations' section
(also added by this PR if not already present from #620).

Co-Authored-By: Oz <oz-agent@warp.dev>
hypnwtykvmpr pushed a commit to hypnwtykvmpr/vampyre that referenced this pull request May 7, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants