# Searchstack MCP server

Source: https://glimind.com/server/mcp-registry%2Fdev.searchstack%2Fsearchstack
Registry id: `mcp-registry/dev.searchstack/searchstack`
Status: auth-required (checked 2026-10-27T04:36:52.239Z)

## Measurements (30 days)

- Uptime: 100%
- Checks: 218
- Outages (90 days): 1

## Install

```json
{
  "mcpServers": {
    "searchstack-mcp-server": {
      "type": "http",
      "url": "https://mcp.searchstack.dev"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http searchstack-mcp-server https://mcp.searchstack.dev
```

## Tools (107)

- `account_get`: Retrieves the details of an Account by name.
- `account_get_name`: Retrieves the account name of the currently authenticated API key.
- `analytics_get_group`: Search analytics for a Group over a UTC date range: total searches, zero-result searches, click-through rate, and the top searches / top zero-result searches. D
- `analytics_get_list`: Search analytics for a List over a UTC date range: total searches, zero-result searches, click-through rate, and the top searches / top zero-result searches. Da
- `api_key_create_read_only`: Mint a strictly read-only API key of any scope (account, list or group) and return its usable value. Only the read/view permissions you request are kept — any w
- `bulk_insert`: Bulk insert Search Results into an existing List. Each item is a free-form field dictionary matching the List's fields.
- `bulk_insert_with_fields`: Bulk insert Search Results, also creating any missing fields from the supplied dictionaries.
- `contributors_create`: Add a Contributor. Contributors can add fields and search results to a List but cannot make breaking changes.
- `contributors_delete`: Remove a Contributor from a List.
- `coordinates_create`: Add a Coordinates field to a List, enabling geographical queries.
- `coordinates_delete`: Remove the Coordinates field from a List. Breaking change: bumps the List version.
- `eval_run`: Start an asynchronous eval run: each query is searched against the pinned records and its hits scored by the judge. Returns a run_id to poll with EvalRunStatus 
- `eval_run_history`: Get an eval set's score history, newest first, paged by an opaque continuation token.
- `eval_run_status`: Poll one eval run: lifecycle status, the environment it ran under (model/reranker/judge), the tally counts and rates, and the per-query rows.
- `eval_set_bootstrap`: Bootstrap an eval set from prior retrieve-then-judge runs: each source run replays its search as one eval query, and the pinned target and judge are taken from 
- `eval_set_create`: Create an eval set against a pinned list/group version. The version is frozen to a concrete number; a pin fixes WHICH RECORDS are searched, not the results (rec
- `eval_set_delete`: Delete an eval set and cascade its runs and per-query rows.
- `eval_set_list`: List the eval sets configured for an Account. An eval set is a named relevance test: query cases pinned to a list/group version and scored by a judge, with a sc
- `eval_set_view`: Get an eval set's configuration (pinned target, judge, context and query cases).
- `extract_document_text`: Extract text from PDF documents attached to a Search Result. Only available when the List's model declares a positive MaxDocumentPages limit.
- `facet_create`: Create a Facet. A Facet is a filterable field (e.g. brand, color, price, category).
- `facet_remove`: Remove a Facet. Breaking change: bumps the List version.
- `facet_rename`: Rename an existing Facet. Breaking change: bumps the List version.
- `facet_values`: List the distinct values of a Facet on a List version. Useful for building filter UIs before searching. Requires the search-result:read permission, like the sea
- `feed_connect`: Connect a credential-light feed (provider must be 'web' for a site crawl or 'api' for an HTTPS endpoint) and return it. Secret-bearing providers (shopify, notio
- `feed_discover`: Preview the pages a proposed web feed scope would crawl, before connecting anything. Returns the discovered pages and whether the preview was truncated. Require
- `feed_edit_interval`: Retune how often a feed polls its source, in minutes. Credential-free.
- `feed_edit_web_scope`: Re-scope a website feed (url_pattern, url_excludes, url_seeds). Web feeds only; carries no secret. Narrowing deactivates now-out-of-scope records on the next sy
- `feed_get`: Get one feed with its current non-secret configuration (web crawl scope, Shopify shop domain, or API endpoint + header name). Secrets are never returned.
- `feed_list`: List the feeds connected to an Account: provider, target media store, staged file path, sync cadence and last-sync state. Credentials are never returned.
- `feed_sync_now`: Queue an immediate sync of a feed from its source, ahead of its scheduled cadence — useful before querying data that must be fresh. An unchanged source stages n
- `get_api_catalog`: Get the Public API discovery catalog (IETF API Catalog draft) with links to OpenAPI, docs, manifest and examples.
- `get_api_info`: Get the Public API self-describing manifest (auth, error codes, MCP integration guidance). Call once per session.
- `get_examples`: Get a curated library of worked request/response examples for the Search Stack Public API.
- `group_add_ip_address`: Add an IP address to a Group's access whitelist.
- `group_add_list`: Add a List (at a version) to a Group.
- `group_bump_version`: Bump a Group's version: re-pins every member List to its latest version and advances current_version. A no-op when every member is already current.
- `group_clone`: Clone a Group into a new Group, copying its configuration and member Lists. By default members are re-pinned to their latest version.
- `group_create`: Create a Group. A Group combines multiple Lists for cross-list searching.
- `group_delete`: Remove a Group.
- `group_edit`: Edit a Group's default search/suggest size and distance unit.
- `group_get`: Get a Group's configuration, member Lists and IP whitelist.
- `group_get_version_members`: Get the member Lists (and pinned versions) that a specific group_version searches.
- `group_get_versions`: List every searchable membership version of a Group. Pass one as group_version to search a frozen set of records.
- `group_remove_ip_address`: Remove an IP address from a Group's access whitelist.
- `group_remove_list`: Remove a List from a Group.
- `group_remove_model`: Remove the embedding model from a Group, reverting it to keyword search.
- `group_remove_reranker`: Detach the reranker from a Group, reverting to score-based ordering.
- `group_restore_version`: Restore a historical membership version as the Group's new current_version (roll-forward, not rewind). Member Lists deleted since that version are skipped and r
- `group_search`: Free-text and/or vector search across a Group of Lists. Hits include 'list_name' so you can tell which list each hit came from.
- `group_search_post`: Free-text and/or vector search across a Group of Lists. POST variant accepting a SearchOptions body.
- `group_set_model`: Set the embedding model for a Group. Member Lists are re-embedded asynchronously.
- `group_set_reranker`: Attach a bring-your-own reranker to a Group.
- `group_suggest`: Typeahead suggestions across all Lists in a Group. Requires the 'list-group:read' permission.
- `group_suggest_post`: Typeahead suggestions across all Lists in a Group. POST variant accepting a SuggestOptions body.
- `group_transfer`: Transfer a Group and its member Lists to a different subscription.
- `judge_create`: Create a bring-your-own LLM judge: a post-search filter that runs your LLM over each candidate and returns a schema-validated verdict. The API key is verified a
- `judge_delete`: Delete a Judge.
- `judge_list`: List the bring-your-own LLM judges configured for an Account (secret API keys omitted).
- `judge_run`: Start an asynchronous batch Judge run over a candidate set. Returns a run_id to poll with JudgeRunStatus; results are produced off the request path.
- `judge_run_status`: Poll a batch Judge run: status, tally (processed/passed/errored) and the per-candidate verdicts persisted so far.
- `judge_try`: Synchronously evaluate a Judge against a single sample candidate — the prompt/schema tuner. Does not persist a run.
- `judge_view`: Get a Judge's configuration (provider, model, instructions, output schema, pass field).
- `list_create`: Create a List. A List is a collection of related Search Results.
- `list_delete`: Permanently delete a List.
- `list_edit`: Edit List defaults and settings.
- `list_get`: Retrieve the details of a List.
- `list_restore_version`: Restore a historical schema version (facets, searchable fields, resources) as the List's new latest version (roll-forward, not rewind). Schema only — Search Res
- `media_store_delete_media`: Permanently delete a media item from a media store.
- `record_group_click`: Records a click-through on a Group search result for analytics, correlated to its query by query_id.
- `record_list_click`: Records a click-through on a List search result for analytics, correlated to its query by query_id.
- `related`: Find Search Results within a List that are vector-similar to a given seed Search Result. Use for 'related items' / 'more like this' flows.
- `related_post`: Find Search Results within a List that are vector-similar to a given seed Search Result. POST variant accepting a RelatedOptions body.
- `resource_create`: Create a Resource. A Resource is a non-searchable, non-filterable field (often a URL).
- `resource_remove`: Remove a Resource. Breaking change: bumps the List version.
- `resource_rename`: Rename an existing Resource. Breaking change: bumps the List version.
- `search_by_image`: Image-similarity search of a List using an absolute, publicly reachable image URL.
- `search_by_image_base64_post`: Image-similarity search of a List using a base64-encoded image. Use when the image cannot be fetched by URL.
- `search_by_image_post`: Image-similarity search of a List using an absolute image URL. POST variant accepting a SearchByImageRequest body.
- `search_group_by_image`: Image-similarity search of a Group using an absolute, publicly reachable image URL. Hits include 'list_name'.
- `search_group_by_image_base64`: Image-similarity search of a Group using a base64-encoded image. Hits include 'list_name'.
- `search_group_by_image_base64_post`: Image-similarity search of a Group using a base64-encoded image. POST variant accepting a SearchByImageBase64Request body.
- `search_group_by_image_post`: Image-similarity search of a Group using an absolute image URL. POST variant accepting a SearchByImageRequest body.
- `search_list`: Free-text and/or vector search of a List version. Returns a SearchResponse JSON document with a 'results' array and 'count'.
- `search_list_post`: Free-text and/or vector search of a List version. POST variant accepting a SearchOptions body. Use when filter/radius strings are long enough to risk URL limits
- `search_result_create`: Create a single Search Result.
- `search_result_delete`: Permanently delete a Search Result.
- `search_result_delete_by_filter`: Queue a background job to permanently delete every Search Result in a List that matches the filter. A filter is required (an empty filter would match the whole 
- `search_result_delete_by_ids`: Synchronously and permanently delete a bounded set of Search Results by id. This is the final step of a move (search -> bulk-insert -> delete exactly the ids ju
- `search_result_edit`: Edit the properties of an existing Search Result.
- `search_result_edit_vector`: Directly update the text and image vectors of an existing Search Result. The List must not be attached to a model.
- `search_result_get`: Fetch a single Search Result by its id, including its fields.
- `search_result_import`: Import a JSON/CSV file from a customer-controlled URL into a List. Optionally creates fields. For structured records you already hold, use bulk-insert instead.
- `search_result_import_from_media`: Import a file already staged in one of the Account's media stores into a List. Set keep_in_sync to re-import automatically whenever the file changes (the feed→l
- `search_result_list`: Browse (list) the Search Results in a List with optional paging, filter, free-text query, geo radius, active flag and ordering. For a ranked/vector search use t
- `search_result_list_post`: Browse (list) the Search Results in a List. POST variant accepting a SearchResultsOptions body — use when the filter string is long enough to risk URL limits.
- `search_result_soft_delete_by_filter`: Queue a background job to soft delete (set active to false on) every Search Result in a List that matches the filter. A filter is required (an empty filter woul
- `searchable_create`: Create a Searchable field.
- `searchable_remove`: Remove a Searchable field. Breaking change: bumps the List version.
- `searchable_rename`: Rename an existing Searchable field. Breaking change: bumps the List version.

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.