Skip to content
Back to search

data-gov-il-mcp

Advanced MCP server for seamless access to Israeli Government Open Data

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/DavidOsherdiagnostica/data-gov-il-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/DavidOsherdiagnostica/data-gov-il-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/davidosherdiagnostica--data-gov-il-mcp/badge.svg)](/listings/davidosherdiagnostica--data-gov-il-mcp)

HTML

<a href="/listings/davidosherdiagnostica--data-gov-il-mcp"><img src="/api/listings/davidosherdiagnostica--data-gov-il-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Claude Desktop / Local Stdio

Use the published package directly:

{
  "mcpServers": {
    "data-gov-il": {
      "command": "npx",
      "args": ["-y", "data-gov-il-mcp"]
    }
  }
}

Streamable HTTP

npm install -g data-gov-il-mcp
data-gov-il-mcp-http

Then configure your MCP client:

{
  "mcpServers": {
    "data-gov-il": {
      "url": "http://localhost:3664/mcp"
    }
  }
}

Docker

docker run -p 3664:3664 ghcr.io/davidosherproceed/data-gov-il-mcp:latest

For local development:

npm install
npm run build
npm run start:stdio
# or
npm run start:http

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 · 428 lines

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

  1. <img width="1024" height="290" alt="gov-mcp" src="https://github.com/user-attachments/assets/e86fed13-3756-43b3-aba8-85778099e9a6" />
  2. # data-gov-il-mcp
  3. Production-grade [Model Context Protocol (MCP)](https://modelcontextprotocol.io) server for Israeli Government Open Data from [data.gov.il](https://data.gov.il).
  4. This server gives MCP-compatible clients structured access to Israeli government datasets, resources, tags, organizations, and tabular records through the official CKAN API. It is written in TypeScript, validates inputs and outputs with Zod, returns JSON-first tool responses, and supports both local `stdio` and remote Streamable HTTP transports.
  5. ## Highlights
  6. | Area | Status |
  7. |---|---|
  8. | MCP tools | 9 tools by default, 10 with optional Sampling enabled |
  9. | MCP resources | 5 static resources + 1 dataset resource template |
  10. | MCP prompts | 3 domain prompts with argument completions |
  11. | Discovery | In-memory catalog snapshot with Hebrew normalization, fuzzy matching, tag ranking, and co-occurrence |
  12. | Transports | `stdio` and Streamable HTTP |
  13. | Auth | `none`, API key bearer auth, OAuth 2.1 JWT/JWKS |
  14. | HTTP hardening | Helmet, CORS, rate limiting, request IDs, Host/Origin validation |
  15. | Responses | `structuredContent` plus identical JSON in `content[0].text` |
  16. | Runtime config | Environment-driven, validated at startup with Zod |
  17. ## Quick Start
  18. ### Claude Desktop / Local Stdio
  19. Use the published package directly:
  20. ```json
  21. {
  22. "mcpServers": {
  23. "data-gov-il": {
  24. "command": "npx",
  25. "args": ["-y", "data-gov-il-mcp"]
  26. }
  27. }
  28. }
  29. ```
  30. ### Streamable HTTP
  31. ```bash
  32. npm install -g data-gov-il-mcp
  33. data-gov-il-mcp-http
  34. ```
  35. Then configure your MCP client:
  36. ```json
  37. {
  38. "mcpServers": {
  39. "data-gov-il": {
  40. "url": "http://localhost:3664/mcp"
  41. }
  42. }
  43. }
  44. ```
  45. ### Docker
  46. ```bash
  47. docker run -p 3664:3664 ghcr.io/davidosherproceed/data-gov-il-mcp:latest
  48. ```
  49. For local development:
  50. ```bash
  51. npm install
  52. npm run build
  53. npm run start:stdio
  54. # or
  55. npm run start:http
  56. ```
  57. ## Catalog Discovery Layer
  58. The server ships with a committed catalog snapshot at `src/data/catalog/catalog.snapshot.json`. The snapshot is generated from data.gov.il and bundled into the build. At startup, it is validated and indexed in memory.
  59. The discovery layer powers:
  60. - `find_datasets` catalog-first search with live CKAN fallback.
  61. - `list_all_datasets` instant local enumeration with optional organization filter.
  62. - `list_organizations` instant local organization list with dataset counts.
  63. - `list_available_tags` and `search_tags` from real CKAN tag/facet data.
  64. - Dynamic completions for `datagov://dataset/{id}`.
  65. - `datagov://tags` and `datagov://catalog/stats` resources.
  66. It includes:
  67. - Hebrew normalization, including nikud removal and final-letter normalization.
  68. - Tokenization and trigram indexes for fuzzy matches and typo tolerance.
  69. - Dataset, tag, and organization maps.
  70. - Tag-to-dataset and organization-to-dataset indexes.
  71. - Tag co-occurrence for related tag suggestions.
  72. - Weighted ranking across exact, token, tag, organization, and fuzzy signals.
  73. Refresh the snapshot:
  74. ```bash
  75. npm run catalog:refresh
  76. npm run build
  77. ```
  78. A scheduled GitHub Actions workflow (`.github/workflows/catalog-refresh.yml`) refreshes the snapshot and opens a PR when catalog data changes.
  79. More detail: [`docs/catalog-discovery-layer.md`](docs/catalog-discovery-layer.md).
  80. ## Tools
  81. All successful tool responses return:
  82. - `structuredContent`: the typed JSON object.
  83. - `content[0].text`: the same object serialized as JSON for text-only clients.
  84. ### Default Tools
  85. | Tool | Purpose |
  86. |---|---|
  87. | `find_datasets` | Primary dataset discovery tool. Uses the local catalog first, then live CKAN fallback when needed. |
  88. | `get_dataset_info` | Full CKAN metadata for a dataset, including tags and resources. |
  89. | `list_all_datasets` | Instant catalog-backed dataset summaries, optionally filtered by organization. |
  90. | `list_resources` | Lists files/datastores inside a dataset and identifies `datastore_active` resources. |
  91. | `search_records` | Queries CKAN datastore records with full-text search, filters, fields, sorting, pagination, and distinct values. |
  92. | `list_organizations` | Catalog-backed organizations with Hebrew titles and dataset counts. |
  93. | `get_organization_info` | Live CKAN organization metadata. |
  94. | `list_available_tags` | Ranked catalog tags with dataset counts and related tags. |
  95. | `search_tags` | Fuzzy tag search with related tag suggestions. |
  96. ### Optional Tools
  97. | Tool | Enabled By | Purpose |
  98. |---|---|---|
  99. | `summarize_dataset` | `MCP_ENABLE_SAMPLING=true` | Requests MCP Sampling from compatible clients to produce a human-readable dataset summary. Falls back to metadata when Sampling is unavailable. |
  100. ### Elicitation in `find_datasets`
  101. `find_datasets` can optionally expose an `interactive` parameter:
  102. ```json
  103. {
  104. "query": "תחבורה",
  105. "interactive": true
  106. }
  107. ```
  108. This is only registered when:
  109. ```bash
  110. MCP_ENABLE_ELICITATION=true
  111. ```
  112. When enabled, compatible clients may show a clarification form for broad searches. For example, the server can ask the user to narrow many matching datasets by publisher organization. If the client does not support Elicitation, the user declines, or the request times out, the tool falls back to normal search results.
  113. This is disabled by default because MCP client support varies.
  114. ## Resources
  115. | URI | Type | Description |
  116. |---|---|---|
  117. | `datagov://organizations` | Static JSON | Organization list from CKAN, cached. |
  118. | `datagov://tags` | Static JSON | Ranked tags from the committed catalog snapshot. |
  119. | `datagov://featured` | Static JSON | Curated high-value datasets with ready-to-use `resource_id` values and field schemas. |
  120. | `datagov://guide` | Static text | Usage guide for tools, resources, and recommended workflows. |
  121. | `datagov://catalog/stats` | Static JSON | Snapshot metadata: generated time, dataset count, tag count, organization count, top organizations. |
  122. | `datagov://dataset/{id}` | Template JSON | Full dataset metadata by dataset slug or ID. Includes dynamic completions and a catalog-backed resource list. |
  123. The server also implements resource subscriptions in a minimal standards-compliant way:
  124. - Advertises `resources.subscribe`.
  125. - Handles `resources/subscribe` and `resources/unsubscribe`.
  126. - Sends `notifications/resources/updated` only for resources a client subscribed to.
  127. - Does not poll CKAN in real time.
  128. ## Prompts
  129. | Prompt | Argument | Purpose |
  130. |---|---|---|
  131. | `food-nutrition-analysis` | `analysis_type` | Food prices, nutrition, kosher, safety, import/export. |
  132. | `environmental-sustainability-analysis` | `analysis_focus` | Air quality, green buildings, waste, water, contaminated sites. |
  133. | `real-estate-market-analysis` | `market_focus` | Housing, urban renewal, subsidized housing, city/property analysis. |
  134. Prompt arguments use MCP completions. Domain focus suggestions are curated, and organization completions are catalog-backed.
  135. ## Optional MCP Client Features
  136. These features are off by default. Enable them only when your target MCP client supports them and you want the server to expose them.
  137. | Variable | Default | Effect |
  138. |---|---|---|
  139. | `MCP_ENABLE_ELICITATION` | `false` | Adds `interactive` to `find_datasets` and allows server-initiated clarification forms. Works in clients such as Cursor and Claude Code. |
  140. | `MCP_ENABLE_SAMPLING` | `false` | Registers `summarize_dataset`, which requests client-side model generation through MCP Sampling. |
  141. Client support differs:
  142. - Cursor supports Elicitation, but does not currently expose Sampling.
  143. - Claude Code supports Elicitation in recent versions.
  144. - Claude Desktop supports many MCP features, but Elicitation support is not reliable/available.
  145. - Sampling availability varies; the server always falls back safely.
  146. ## Configuration
  147. Copy `.env.example` to `.env`:
  148. ```bash
  149. cp .env.example .env
  150. ```
  151. ### Core
  152. | Variable | Default | Description |
  153. |---|---|---|
  154. | `TRANSPORT` | `stdio` | Default transport when using the generic entry point. Dedicated binaries are also available. |
  155. | `PORT` | `3664` | HTTP port. |
  156. | `HOST` | `0.0.0.0` | HTTP bind host. |
  157. | `CORS_ORIGIN` | `*` | Allowed CORS origins. Avoid wildcard in production browser deployments. |
  158. | `LOG_LEVEL` | `info` | `fatal`, `error`, `warn`, `info`, `debug`, or `trace`. |
  159. | `NODE_ENV` | `production` | `development`, `production`, or `test`. |
  160. ### CKAN
  161. | Variable | Default | Description |
  162. |---|---|---|
  163. | `CKAN_BASE_URL` | `https://data.gov.il/api/3/action` | CKAN action API base URL. |
  164. | `CKAN_TIMEOUT_MS` | `10000` | Default CKAN request timeout. |
  165. | `CKAN_SEARCH_TIMEOUT_MS` | `15000` | Timeout for heavier datastore/search requests. |
  166. | `CACHE_TTL_MS` | `300000` | Default cache TTL. |
  167. | `CACHE_MAX_ITEMS` | `500` | Max entries per in-memory cache. |
  168. ### HTTP Hardening
  169. | Variable | Default | Description |
  170. |---|---|---|
  171. | `TRUST_PROXY` | `false` | Trust reverse proxy headers. Set when behind nginx/Caddy/ALB. |
  172. | `RATE_LIMIT_WINDOW_MS` | `60000` | Rate limit window. Set `0` to disable. |
  173. | `RATE_LIMIT_MAX` | `120` | Requests per IP per window. Set `0` to disable. |
  174. | `ALLOWED_HOSTS` | empty | Host allowlist for DNS rebinding protection. Defaults to loopback/local hosts when unset. |
  175. | `ALLOWED_ORIGINS` | empty | Browser Origin allowlist. Falls back to `CORS_ORIGIN` when appropriate. |
  176. ### Authentication
  177. | Variable | Default | Description |
  178. |---|---|---|
  179. | `AUTH_MODE` | `none` | `none`, `apikey`, or `oauth`. |
  180. | `API_KEYS` | empty | Comma-separated bearer tokens for `AUTH_MODE=apikey`. |
  181. | `OAUTH_ISSUER` | unset | Expected JWT issuer for `AUTH_MODE=oauth`. |
  182. | `OAUTH_AUDIENCE` | unset | Expected JWT audience for `AUTH_MODE=oauth`. |
  183. | `OAUTH_JWKS_URI` | unset | JWKS URL for JWT verification. |
  184. | `OAUTH_RESOURCE_SERVER` | unset | Canonical MCP resource URL for OAuth protected resource metadata. Usually includes `/mcp`. |
  185. ### Service Identity
  186. | Variable | Default | Description |
  187. |---|---|---|
  188. | `SERVICE_NAME` | package/server default | MCP server name override. |
  189. | `SERVICE_VERSION` | package version | MCP server version override. |
  190. | `SERVICE_DESCRIPTION` | built-in description | MCP server semantic description override. |
  191. ## Recommended Workflows
  192. ### Find and Query a Dataset
  193. 1. Use `find_datasets` with natural Hebrew or English terms.
  194. 2. Use `get_dataset_info` or `list_resources` for a chosen dataset.
  195. 3. Pick a resource with `datastore_active=true`.
  196. 4. Use `search_records` with `limit=5` first to inspect fields.
  197. 5. Add `filters`, `fields`, `sort`, `distinct`, or pagination as needed.
  198. Example flow:
  199. ```text
  200. find_datasets({ "query": "מחיר למשתכן" })
  201. get_dataset_info({ "dataset": "mechir-lamishtaken" })
  202. search_records({
  203. "resource_id": "7c8255d0-49ef-49db-8904-4cf917586031",
  204. "limit": 5,
  205. "include_total": true
  206. })
  207. ```
  208. ### Discover Tags
  209. ```text
  210. search_tags({ "keyword": "דיור", "limit": 5 })
  211. find_datasets({ "query": "תחבורה", "tags": "תחבורה ציבורית" })
  212. ```
  213. ### Use Interactive Discovery
  214. Requires:
  215. ```bash
  216. MCP_ENABLE_ELICITATION=true
  217. ```
  218. Then an agent may call:
  219. ```text
  220. find_datasets({ "query": "תחבורה", "interactive": true })
  221. ```
  222. Compatible clients may show a form asking the user to narrow results.
  223. ### Use Client-Side Summaries
  224. Requires:
  225. ```bash
  226. MCP_ENABLE_SAMPLING=true
  227. ```
  228. Then:
  229. ```text
  230. summarize_dataset({ "dataset": "mechir-lamishtaken", "language": "he" })
  231. ```
  232. If Sampling is unavailable, the tool returns the dataset metadata and `sampling.used=false`.
  233. ## Development
  234. ```bash
  235. npm install
  236. # Type-check
  237. npm run typecheck
  238. # Lint
  239. npm run lint
  240. # Test
  241. npm test
  242. # Build
  243. npm run build
  244. # Refresh local catalog snapshot
  245. npm run catalog:refresh
  246. ```
  247. Run locally:
  248. ```bash
  249. # stdio
  250. npm run build
  251. npm run start:stdio
  252. # HTTP
  253. npm run build
  254. npm run start:http
  255. ```
  256. Enable optional features locally:
  257. ```bash
  258. MCP_ENABLE_ELICITATION=true MCP_ENABLE_SAMPLING=true npm run start:http
  259. ```
  260. On PowerShell:
  261. ```powershell
  262. $env:MCP_ENABLE_ELICITATION="true"
  263. $env:MCP_ENABLE_SAMPLING="true"
  264. npm run start:http
  265. ```
  266. ## Project Structure
  267. ```text
  268. src/
  269. auth/ Authentication providers and Express middleware
  270. bin/ stdio and HTTP entry points
  271. cache/ In-memory TTL/LRU cache
  272. catalog/ Snapshot validation, indexing, fuzzy search, CatalogService
  273. ckan/ Typed CKAN API client and CKAN response types
  274. config/ Zod env config, constants, server identity
  275. core/ Dependency container, MCP server factory, lifecycle
  276. data/catalog/ Committed catalog snapshot artifact
  277. formatting/ JSON response builders and guidance text
  278. observability/ Pino logger
  279. prompts/ MCP prompt definitions, templates, registration
  280. resources/ MCP resources, templates, subscriptions
  281. services/ Domain services for CKAN data access
  282. tools/ MCP tool definitions and Zod schemas
  283. transports/ stdio and Streamable HTTP transports
  284. tests/
  285. fixtures/ Test fixtures
  286. unit/ Unit tests
  287. scripts/
  288. refresh-catalog.ts
  289. docs/
  290. catalog-discovery-layer.md
  291. MIGRATION.md
  292. ```
  293. ## Docker
  294. ```bash
  295. docker build -t data-gov-il-mcp .
  296. docker run -p 3664:3664 data-gov-il-mcp
  297. ```
  298. With optional features:
  299. ```bash
  300. docker run -p 3664:3664 \
  301. -e MCP_ENABLE_ELICITATION=true \
  302. -e MCP_ENABLE_SAMPLING=true \
  303. data-gov-il-mcp
  304. ```
  305. ## Quality
  306. The project is expected to pass:
  307. ```bash
  308. npm run typecheck
  309. npm run lint
  310. npm test
  311. npm run build
  312. ```
  313. Current implementation includes unit coverage for environment parsing, auth providers, CKAN errors, cache, formatting, catalog text normalization/fuzzy/index/search logic, snapshot validation, services, resources, subscriptions, and HTTP Host/Origin guard.
  314. ## License
  315. [MIT](LICENSE)

Ratings and comments

Sign in to rate this skill.

Sign in

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