# io.github.cyanheads/oecd-mcp-server

> Search and query 1,500+ OECD statistical datasets via SDMX. Keyless.

- name: io.github.cyanheads/oecd-mcp-server
- version: 0.4.0
- connection class: R0 (autonomous)
- trust: 94/100
- quality: 89/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.cyanheads%2Foecd-mcp-server
- tools: https://api.protogrid.dev/v1/servers/io.github.cyanheads%2Foecd-mcp-server/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "oecd-mcp-server": {
      "type": "http",
      "url": "https://oecd.caseyjhand.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 80
- drivers: +repository +namespace-matches-repo +reachable +uptime-100% +updated-16d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 89/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 86 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 7 of 7 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: oecd_get_dimension_values (destructiveHint); oecd_list_agencies (destructiveHint); oecd_search_datasets (destructiveHint); …
- pass `tools.token_cost`: about 1,962 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: deps.dev does not know @cyanheads/oecd-mcp-server@0.4.0, @cyanheads/oecd-mcp-server@0.4.0

- tools: 7, about 1,962 tokens to load them all
- tool set hash: 5a76987bbc7c922a588ea41ad5afbe3c
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.cyanheads/oecd-mcp-server.svg)](https://protogrid.dev/servers/io.github.cyanheads/oecd-mcp-server)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Dependencies

- npm @cyanheads/oecd-mcp-server@0.4.0: unknown
- npm @cyanheads/oecd-mcp-server@0.4.0: unknown

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://oecd.caseyjhand.com/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

- npm @cyanheads/oecd-mcp-server@0.4.0
- npm @cyanheads/oecd-mcp-server@0.4.0

## Tools (7)

- `oecd_dataframe_describe`: List tables and columns staged on a DataCanvas by a prior oecd_query_dataset spill. Call this before oecd_dataframe_query to discover exact table and column names for SQL. Only available when CANVAS_PROVIDER_TYPE=duckdb is set.
- `oecd_dataframe_query`: Run a read-only SQL SELECT against OECD observation tables staged on a DataCanvas by oecd_query_dataset. Call oecd_dataframe_describe first to discover exact table and column names, then use this tool for aggregation, filtering, GROUP BY, JOIN, and window functions. Only available when CANVAS_PROVIDER_TYPE=duckdb is set.
- `oecd_get_dataset_info`: Fetch a dataflow's dimensions, their order, and how to construct a query key. Returns per-dimension names, codelist references, and position in the dot-delimited key. Required before calling oecd_query_dataset to understand key structure.
- `oecd_get_dimension_values`: Fetch the valid codes and labels for one dimension of a dataflow. Use to resolve human-readable names (countries, measures) to SDMX codes before querying with oecd_query_dataset. Pass query to match a code or label by substring — codelists run to a thousand-plus entries, and the response is a page of at most limit codes either way.
- `oecd_list_agencies`: List OECD SDMX agencies, the directorate each belongs to, and the number of dataflows each publishes. Use to discover agency IDs before filtering oecd_search_datasets by department.
- `oecd_query_dataset`: Fetch observations from an OECD dataflow filtered by a dimension key and optional time range. Returns decoded rows (one per observation) with dimension and attribute labels, and values already scaled by the observation unit multiplier. Large multi-country time-series spill to a DataCanvas table — follow up with oecd_dataframe_query; without DataCanvas every row still comes back, but the rendered table stops at a preview slice. Call oecd_get_dataset_info first to learn the dimension order for constructing the key.
- `oecd_search_datasets`: Search OECD dataflows by keyword or theme, matching against dataflow names and descriptions. Returns flow_ref identifiers, names, and agency IDs for use with oecd_get_dataset_info.