MCP SERVERStand up a retrieval namespace with its own storage and embedding configuration, ingest text, files, URLs, sitemaps, whole sites and connected drives, then search it semantically or hybrid.
LABSCO SUMMARY
createNamespace takes file storage, vector storage and embedding model configuration together, which puts those choices before the first document rather than after it — and resyncDocuments exists for when they change, naming a schema change as the reason to reprocess. The connector path has a consequence worth reading first: ingestConnector works from the document ids already in the backlog because the user picked them during authorisation, and when they are not there the user has to go through the authorisation flow again to pick them. hybridSearch requires an explicit hybridConfig with weights for keyword and semantic matching, so the balance between exact terms and meaning is a decision you make rather than a default you inherit.
A retrieval-augmented ingestion and search client with 25 tools covering namespaces, ingestion from many sources, document management and resync, semantic and hybrid search, and third-party connection lifecycle.
A SourceSync API key in SOURCESYNC_API_KEY; SOURCESYNC_NAMESPACE_ID (a default namespace) and SOURCESYNC_TENANT_ID are optional. A namespace has to exist with its file storage, vector storage and embedding model configured before anything can be ingested into it.
One command plus a key — env SOURCESYNC_API_KEY=<YOUR_SOURCESYNC_API_KEY> npx -y sourcesyncai-mcp
USE CASES
Create the namespace with its own configuration rather than inheriting a default, and confirm the key works before loading anything into it.
Ingest from a sitemap, a crawl of the site, or a connected source, and watch the job rather than assuming it finished.
Run semantic search when the wording will not match, and hybrid when an exact term matters — then fetch the documents behind the hits.
Resync documents whose source moved on, update the ones that changed, and delete what should no longer be retrievable.
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
createConnectionCreates a new connection to a specific source. The connector parameter should be a valid SourceSync connector enum value. The clientRedirectUrl parameter is optional and can be used to specify a custom redirect URL for the connection. This will give you a authorization url which you can redirect the user to. The user will then be asked to pick the documents they want to ingest.
createNamespaceCreates a new namespace with the provided configuration. Requires a name, file storage configuration, vector storage configuration, and embedding model configuration.
deleteDocumentsPermanently deletes documents that match the specified filter criteria.
deleteNamespacePermanently deletes a namespace by its ID.
fetchDocumentsFetches documents from the namespace based on filter criteria. Supports pagination and including specific document properties.
fetchUrlContentFetches the content of a URL. Particularly useful for fetching parsed text file URLs.
getConnectionRetrieves details for a specific connection by its ID.
getIngestJobRunStatusChecks the status of a previously submitted ingestion job.
getNamespaceRetrieves a specific namespace by its ID.
hybridSearchPerforms a combined keyword and semantic search, balancing between exact matches and semantic similarity. Requires hybridConfig with weights for both search types.
ingestConnectorIngests all documents in the connector that are in backlog or failed status. No need to provide the document ids or file ids for the ingestion. Ids are already in the backlog when picked thorough the picker. If not, the user has to go through the authorization flow again, where they will be asked to pick the documents again.
ingestFileIngests a file into the namespace. Supports various file formats with automatic parsing.
ingestSitemapIngests content from a website using its sitemap.xml. Supports path filtering and link limits.
ingestTextIngests raw text content into the namespace. Supports optional metadata and chunk configuration.
ingestUrlsIngests content from a list of URLs. Supports scraping options and metadata.
ingestWebsiteCrawls and ingests content from a website recursively. Supports depth control and path filtering.
listConnectionsLists all connections for the current namespace, optionally filtered by connector type.
listNamespacesLists all namespaces available for the current API key and optional tenant ID.
resyncDocumentsReprocesses documents that match the specified filter criteria. Useful for updating after schema changes.
revokeConnectionRevokes access for a specific connection, removing the integration with the external service.
semanticSearchPerforms semantic search across the namespace to find relevant content based on meaning rather than exact keyword matches.
updateConnectionUpdates a connection to a specific source. The connector parameter should be a valid SourceSync connector enum value. The clientRedirectUrl parameter is optional and can be used to specify a custom redirect URL for the connection. This will give you a authorization url which you can redirect the user to. The user will then be asked to pick the documents they want to ingest. This is useful if you want to update the connection to a different source or if you want to update the clientRedirectUrl or if you want to pick a different or new set of documents.
updateDocumentsUpdates metadata for documents that match the specified filter criteria.
updateNamespaceUpdates an existing namespace with the provided configuration parameters.
validateApiKeyValidates the API key by attempting to list namespaces. Returns the list of namespaces if successful.
BEFORE YOU INSTALL
25 tools when we connected. The tools are camelCase, and the documentation's snake_case names such as ingest_text no longer exist. The per-connector ingest tools are now a single ingestConnector, ingestFile is undocumented, and getDocuments is now fetchDocuments.
CONTEXT COST
Rated by the size of the 25 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
env SOURCESYNC_API_KEY=<YOUR_SOURCESYNC_API_KEY> npx -y sourcesyncai-mcp{
"mcpServers": {
"sourcesyncai-mcp": {
"command": "npx",
"args": [
"-y",
"sourcesyncai-mcp"
],
"env": {
"SOURCESYNC_API_KEY": "<YOUR_SOURCESYNC_API_KEY>",
"SOURCESYNC_NAMESPACE_ID": "<YOUR_SOURCESYNC_NAMESPACE_ID>",
"SOURCESYNC_TENANT_ID": "<YOUR_SOURCESYNC_TENANT_ID>"
}
}
}
}Only SOURCESYNC_API_KEY is required. SOURCESYNC_NAMESPACE_ID sets a default namespace and SOURCESYNC_TENANT_ID is optional — delete either line if you do not use it.
npx -y @smithery/cli install @pbteja1998/sourcesyncai-mcp --client claudeMCP servers
lyonzin
pinecone-io
tomohiro-owada
akshay2211