Skip to content
Back to search

solana-mcp-official

Try it out at https://mcp.solana.com !

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/solana-foundation/solana-mcp with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/solana-foundation/solana-mcp'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/solana-foundation--solana-mcp-official/badge.svg)](/listings/solana-foundation--solana-mcp-official)

HTML

<a href="/listings/solana-foundation--solana-mcp-official"><img src="/api/listings/solana-foundation--solana-mcp-official/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 57 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # Official Solana MCP Server
  2. Try it out at https://mcp.solana.com !
  3. The official Solana Developer MCP. Purpose: serve up-to-date documentation across the Solana ecosystem to AI agents and developer tooling.
  4. ## Architecture
  5. - **Ingestion** ([`ingestion/`](ingestion/)): Databricks notebook crawls the sources listed in [`ingestion/sources.yaml`](ingestion/sources.yaml), chunks markdown, and writes embeddings into a Delta-backed Vector Search index.
  6. - **Retrieval** ([`lib/services/databricks/`](lib/services/databricks/)): MCP tools query the index via the Databricks managed AI Search MCP server, which retrieves and reranks results server-side. `get_documentation` falls back to a SQL read of the `docs_chunks` Delta table when a source has no published `llms.txt`.
  7. - **Server** ([`lib/index.ts`](lib/index.ts), [`server/cloudrun.ts`](server/cloudrun.ts)): Exposes five tools over MCP — `Solana_Expert__Ask_For_Help` and `Solana_Documentation_Search` (semantic RAG), `list_sections` and `get_documentation` (canonical-spec retrieval modelled after the Svelte AI server), and `program_autofixer` for Anchor and Pinocchio Solana program Rust checks. Deployed on Cloud Run as a containerised Node service fronting `mcp.solana.com`; calls the Databricks workspace REST API directly for retrieval.
  8. - **Section catalogue** ([`ingestion/sources.yaml`](ingestion/sources.yaml) → [`lib/sources.generated.ts`](lib/sources.generated.ts)): `pnpm gen:sources` emits a typed catalogue of every source, its tags from a closed 22-section taxonomy, and `use_cases` keywords used by `list_sections` to route the agent.
  9. - **Analytics** ([`lib/services/s3/analytics.ts`](lib/services/s3/analytics.ts)): Tool calls + initializations are buffered in memory and uploaded as JSONL objects to the S3 prefix configured by `ANALYTICS_S3_URI`.
  10. ## CLI
  11. [`cli/`](cli/) ships `@solana/mcp`, a dependency-free command-line client for agents and scripts without MCP support. Each command is one `tools/call` against `mcp.solana.com`, so it needs no credentials.
  12. ```bash
  13. npx @solana/mcp search "derive a PDA with Anchor"
  14. npx @solana/mcp ask "why does my CPI fail with PrivilegeEscalation?"
  15. npx @solana/mcp sections
  16. npx @solana/mcp docs anchor-docs frameworks
  17. npx @solana/mcp check programs/vault/src/lib.rs # or: cat lib.rs | npx @solana/mcp check -
  18. ```
  19. Add `--json` for the raw tool result, and `--framework anchor|pinocchio` to `check` when the framework is not detected from imports. Exit codes: `0` ok, `1` `check` found a syntax error or an undismissed critical/high issue, `2` usage, network, or server error. Set `SOLANA_MCP_URL` to point at another server, e.g. `http://localhost:8080/mcp`.
  20. To release, bump `version` in [`cli/package.json`](cli/package.json), merge, then run the [`Publish CLI`](.github/workflows/publish-cli.yml) workflow from `main` (dry run first). It publishes to npm through Trusted Publishing and creates a `cli-v<version>` GitHub release.
  21. ## Local Development
  22. ```bash
  23. pnpm install
  24. cp .env.example .env # set DATABRICKS_HOST + DATABRICKS_TOKEN + DATABRICKS_VS_INDEX
  25. pnpm dev:local
  26. pnpm inspector # connects MCP Inspector at http://127.0.0.1:6274
  27. ```
  28. ## Deploy
  29. Production runs on Cloud Run (mcp.solana.com → [`server/cloudrun.ts`](server/cloudrun.ts), built via the root [`Dockerfile`](Dockerfile)). Push to `main` triggers [`.github/workflows/deploy-cloudrun.yml`](.github/workflows/deploy-cloudrun.yml), which submits a Cloud Build and rolls the new revision. Runtime env vars (`DATABRICKS_HOST`, `DATABRICKS_TOKEN`, `DATABRICKS_VS_INDEX`, `DATABRICKS_WAREHOUSE_ID`, `ANALYTICS_S3_*`, `AWS_*`) and deploy config (`GCP_*`, `VPC_CONNECTOR`) are loaded from the Doppler `prd_github` config at deploy time.
  30. The Databricks side ([`databricks.yml`](databricks.yml)) deploys two resources via `just deploy`:
  31. - the daily ingestion job (`crawl_and_index.py` notebook) — crawls sources, MERGEs into Delta, syncs the Vector Search index;
  32. - the Lakeview dashboard. Analytics source files land in S3 and require downstream ingestion before dashboard consumption.
  33. Per-environment values (catalog, warehouse, index) live in the gitignored `prod.yml` (see template inline in `databricks.yml`).
  34. ```bash
  35. just deploy # builds, pushes ingestion job + dashboard
  36. ```
  37. ## Evals
  38. Per-environment values (catalog, warehouse, index) live in the gitignored `prod.yml`; supply each variable listed under `variables:` in [`databricks.yml`](databricks.yml).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.