Skip to main content
Glama
649,985 tools. Updated 2026-10-09 09:26

"Creating a Custom Local Knowledge Base" matching MCP tools:

  • Create a local container snapshot (async). Runs in background — returns immediately with status "creating". Poll list_snapshots() to check when status becomes "completed" or "failed". Available for VPS, dedicated, and cloud plans (any plan with max_snapshots > 0). Local snapshots are stored on the host disk and count against disk quota. Requires: API key with write scope. Args: slug: Site identifier description: Optional description (max 200 chars) Returns: {"id": "uuid", "name": "snap-...", "status": "creating", "storage_type": "local", "message": "Snapshot started. Poll list_snapshots() to check status."} Errors: VALIDATION_ERROR: Max snapshots reached or insufficient disk quota
    ConnectorNo auth
  • List merchant knowledge base documents (uploads + scraped URLs). Use reviewStatus/syncable to see what is ready for agent retrieval. Pass `updatedAfter` for delta sync. Reviewed content is fetched via GET /v6/merchant/ai/knowledge/{id}/content; source audit text is available with ?variant=extracted.
    ConnectorNo auth
  • List merchant knowledge base documents (uploads + scraped URLs). Use reviewStatus/syncable to see what is ready for agent retrieval. Pass `updatedAfter` for delta sync. Reviewed content is fetched via GET /v6/merchant/ai/knowledge/{id}/content; source audit text is available with ?variant=extracted.
    ConnectorNo auth
  • Answer a question about Trooth itself (what the Trooth Network is, what one company record carries, pricing, how witnessing works) from Trooth's fixed, curated knowledge base. Makes no outside request. A question the knowledge base does not cover returns out_of_scope; for a company's record use trooth_public_trust_profile.
    ConnectorNo auth

Matching MCP Servers

  • A
    license
    Not graded
    quality
    C
    maintenance
    Provides cited retrieval over local-first knowledge sources (TXT, CSV, Google Sheets, Zoho Mail, MBOX) via SQLite FTS5, with tools for searching and checking source status, returning evidence links instead of generated answers.
    MIT

Matching MCP Connectors

  • A searchable knowledge base your assistant reads and writes.

  • Search verified local businesses, check what their verification proves, and message them.

  • Puts CONTENT INTO a knowledge base. This is not the tool that makes a knowledge base reachable from an agent — that is findagent_attach_kb, which connects an existing base to an agent, department or organization. Add a text document to a knowledge base you own by pasting its content. It ingests asynchronously (parse → structure-aware chunk → embed with the KB’s bound key). Content is de-duplicated by hash: re-adding the exact same text is a no-op (the response `deduped` flag is true, no second document). Requires the KB to have an embedding key bound, or the document will not ingest. For files (PDF/markdown/docx), use the web Knowledge Base uploader.
    ConnectorOAuth
  • Get the current knowledge-base snapshot/version id. Pin this kb_snapshot for reproducibility: the same query against the same kb_snapshot returns identical results.
    ConnectorNo auth
  • Define a new custom post type (e.g. "treatment", "service"). Required before creating posts of that type. After creating a post type, use create_post_type_field to define its structured field schema. Those fields are stored in meta on each post — do not use excerpt for structured data.
    ConnectorNo auth
  • Get summary statistics of the Klever VM knowledge base. Returns total entry count, counts broken down by context type (code_example, best_practice, security_tip, etc.), and a sample entry title for each type. Useful for understanding what knowledge is available before querying.
    ConnectorNo auth
  • Define a new custom post type (e.g. "treatment", "service"). Required before creating posts of that type. After creating a post type, use create_post_type_field to define its structured field schema. Those fields are stored in meta on each post — do not use excerpt for structured data.
    ConnectorNo auth
  • Train the AI agent by adding a knowledge source. type='url' crawls a website (up to 50 pages, fewer when the workspace knowledge-base quota is nearly full); type='qa' stores a single question/answer pair. Ingestion is asynchronous, the source starts as PENDING; poll `list_knowledge` for READY status.
    ConnectorNo auth
  • Semantic search over the workspace knowledge base. Returns the most relevant chunks (with source document title and similarity score) for a query. Only searches documents that have finished training (status READY).
    ConnectorNo auth
  • List the knowledge-base documents backing the website chatbot — file names, sizes, upload dates and a text preview.
    ConnectorNo auth
  • List where a knowledge base you own is attached (agent / department / personal), each with its attachment id and mode (tool | auto_inject | both). Use an attachment id with findagent_detach_kb to remove that one binding. READ-ONLY.
    ConnectorOAuth
  • Detach a knowledge base from an agent, department, or your personal binding by attachment_id (from findagent_list_kb_attachments). This removes only that one binding — the knowledge base itself and any other attachments are unchanged. Owner-gated.
    Connector
    Destructive
    OAuth
  • Permanently delete an ENTIRE knowledge base you own, including all of its documents, chunks, structure, and attachments. Owner-gated (deleting a SHARED organization knowledge base requires an organization owner or admin). Any agent it was attached to loses access. This cannot be undone.
    Connector
    Destructive
    OAuth
  • Ask the Ergora Business legal — contracts, IP, compliance, startup law (not legal advice). Returns summarised, cited insights from a curated knowledge base of leading practitioners, books and research.
    ConnectorNo auth