Sprigr
Sprigr does the admin between the tools your business already runs on. Invoices matched, forms filled, approvals routed, reports sent. You sign off on the big ones.
https://sprigr.com/Connect straight to this server’s public endpoint.
https://mcp.sprigr.com/mcpWe add this server to your workspace, walk through sign-in once, then open Studio with tools ready to run.
Last probed Sep 14, 2026 · mcp.sprigr.com
20tools discovered
Signup
Get instructions for creating a Sprigr account and API key. Accounts are created at the Sprigr Platform (platform.sprigr.com), not through this tool. No authentication required.
List Indexes
List all search indexes in your Sprigr account. Shows index names, object counts, descriptions, and when they were last updated.
Create Index
Create a new search index and configure its settings. Specify which attributes should be searchable (for full-text queries) and which should be available as facets (for filtering and counting). You MUST declare attributes_for_faceting here before you can use filters in search.
Update Settings
Update settings for an existing search index. Change searchable attributes, faceting, ranking, or synonyms. MIGRATION: re-applying semantic_search: true also re-embeds any long documents still carrying a single pre-chunking vector, upgrading them to chunked embeddings (response reports _embeddings_rechunked; if _embeddings_deferred appears, call again to continue).
Import Objects
Import (upsert) JSON objects into a search index. Each object must have a unique objectID. If an object with the same objectID already exists, it is replaced. The index is created automatically if it does not exist. Maximum 1000 objects per call. Imports are accepted asynchronously: the result carries a taskID and the write is usually visible within seconds. To confirm a write landed, poll GET /1/indexes/:index/task/:task_id (REST) for status "published". TIP: Include a "_keywords" string field
Smart Import
Dedup-aware insert for AI-AGENT MEMORY. Before storing a fact, it checks the target index for an existing near-duplicate and either updates that record in place (duplicate), replaces it with newer info while keeping history (supersede), or inserts a new record (independent). Use this for memory/notes/context indexes where saving the same fact under a new objectID would silently create near-duplicates. Do NOT use this for product catalogs, emails, or other real-object storage where near-identical
Search
Search an index with full-text search, optionally with semantic (vector) search. Supports facet filtering, facet counts, and pagination. Use filters to narrow results by attribute values (e.g. "genre:Sci-Fi"). Use facets to get value counts for attributes (e.g. see how many hits per genre). Set semantic: true for hybrid keyword + semantic search (requires semantic_search enabled on the index). Hybrid search uses Reciprocal Rank Fusion to combine keyword and vector results. Use match_mode: "exact
Get Stats
Get statistics for your Sprigr account: index count, total objects, storage used.
Delete Objects
Delete objects from an index by their objectIDs. Maximum 1000 IDs per call.
Get Object
Fetch a single object from an index by its objectID. Useful for retrieving a specific record without searching.
Delete Index
Permanently delete an entire index, including all its objects, facet data, and settings. This action cannot be undone.
Clear Index
Remove all objects from an index but keep the index settings (searchable attributes, facets, etc.). Useful for rebuilding data without reconfiguring the index.
Export Objects
Export (download) all objects from an index as JSON. Supports pagination for large indexes. Returns up to 1000 objects per page. Use page parameter to iterate through all data.
Multi Search
Search across multiple indexes in a single call. Returns results from each index tagged with their source. Useful for searching across all your data at once instead of making separate calls. Supports semantic, match_mode, and min_vector_similarity (same semantics as single-index search).
Set Alias
Point an alias name at a real index. After setting, you can use the alias name anywhere you would use an index name (search, import, get_object, etc.). Useful for zero-downtime reindexing: build a new index, then swap the alias.
Delete Alias
Remove an index alias. After deleting, the alias name will no longer resolve to any index.
List Aliases
List all index aliases in your account. Shows which alias points to which real index.
Create Api Key
Create a new API key for your Sprigr account. Use this to create restricted keys for sub-agents or integrations that should only access specific indexes. Requires an admin-level API key.
Create Secured Key
Mint a SECURED (scoped) API key from your SEARCH key. A secured key carries a locked filter that the engine AND-s into every query the key makes, and the holder cannot remove or alter it. Use it for per-end-user authorization: give an AI agent a key whose filter restricts results to rows that one user is allowed to see (e.g. document ACLs). The key is stateless — nothing is stored — so revoke by rotating the parent search key or by setting validUntil. Requires a search-level API key.
List Api Keys
List all API keys in your account with their types and index restrictions. Shows masked key previews (last 4 characters). Requires admin-level API key.
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
Directory coverage for brandsSprigr does the admin between the tools your business already runs on. Invoices matched, forms filled, approvals routed, reports sent. You sign off on the big ones.
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
Operate Sprigr? Verify ownership to take over this directory entry.
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.
MCPBundles probed 20 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
Sprigr may require signing in to the provider before tools can run. Connect through MCPBundles or your MCP client and complete any provider login when prompted.
MCPBundles is an independent platform built on the open Model Context Protocol standard. Not affiliated with Anthropic PBC or Claude.