claix

Endpoint

Hosted endpoint · transport

Connect

This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):

For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:

If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:

Tool quality observed · not scored

From an anonymous initialize + tools/list capture measured 2026-10-20; tokens are chars/3.6 of each tool definition. Recorded for the Kin Score's agent readiness as an observed signal — it contributes no points yet.

Tools

• claix.schemas.list — List the Claix schemas available for the authenticated account. Returns id, name, type, schema_definition, is_agent_mode, and agent_definition. Call this first whenever you need a schema_id before claix.extract.* or claix.agent.* tools.
• claix.schemas.create — Create a Claix schema (POST /api/create-schema). Requires name, type (excel-json, json-excel, pdf-json, doc-json, img-json, txt-json, audio-json) and schema_definition. Optional: is_agent_mode, agent_definition, resumen_agent, window_context, window_time (minutes or "infinity" for Persistent Mode), source verification (default false).
• claix.schemas.delete — Delete a Claix schema owned by the API key (POST /api/delete-schema). Requires schema_id.
• claix.extract.excel — Extract structured JSON from an Excel (.xlsx) or CSV file using a Claix excel-json schema. Processes the first sheet only. Returns typed JSON matching the schema plus log_id. If source verification is enabled on the schema, each field is {value, source} instead of a bare value. Use when the user attaches a spreadsheet or CSV.
• claix.extract.pdf — Extract structured JSON from a PDF (text or scanned, max 15 MB) using a Claix pdf-json schema. Returns a single JSON object in data[] plus log_id. If source verification is enabled on the schema, each field is {value, source}. Use for invoices, contracts, forms, or reports.
• claix.extract.doc — Extract structured JSON from a Word document (.docx, .txt, .md, .rtf; max 10 MB) using a Claix doc-json schema. Returns log_id. If source verification is enabled on the schema, each field is {value, source}. Legacy .doc is not supported.
• claix.extract.image — Extract structured JSON from a visible image (JPEG, PNG, WebP, HEIC/HEIF; max 15 MB) using a Claix img-json schema. Returns log_id. If source verification is enabled on the schema, each field is {value, source}. Use for photos of documents, tickets, or labels.
• claix.extract.text — Extract structured JSON from already processed plain text, HTML, or XML using a Claix txt-json schema. Send the payload in the content field (no file). Max 300,000 characters. Returns log_id. If source verification is enabled on the schema, each field is {value, source}. POST /api/txt-json.
• claix.extract.audio — Extract structured JSON from spoken audio (MP3, WAV, M4A, OGG; max 12 MB / 10 minutes) using a Claix audio-json schema. Returns log_id. If source verification is enabled on the schema, each field is {value, source}. Unintelligible audio returns HTTP 422. Use for calls, meetings, voice notes, or dictations.
• claix.convert.json_to_excel — Convert JSON to an Excel .xlsx file using a Claix json-excel schema. Provide json_data inline or file_base64 with a .json file. Returns base64-encoded xlsx on success.
• claix.agent.excel — Run Excel/CSV extraction plus Agent mode semantic reasoning. Requires is_agent_mode on the schema. Returns data[], agent_data, and log_id. If source verification is enabled on the schema, extracted fields and agent_data are {value, source}.
• claix.agent.pdf — Run PDF extraction plus Agent mode reasoning. Requires is_agent_mode. Returns structured data[], agent_data, and log_id. If source verification is enabled on the schema, fields are {value, source}.
• claix.agent.doc — Run document extraction plus Agent mode reasoning on .docx/.txt/.md/.rtf. Requires is_agent_mode. Returns data[], agent_data, and log_id. If source verification is enabled on the schema, fields are {value, source}.
• claix.agent.image — Run image extraction plus Agent mode reasoning. Requires is_agent_mode. Returns data[], agent_data, and log_id from visible content. If source verification is enabled on the schema, fields are {value, source}.
• claix.agent.text — Run text/HTML/XML extraction plus Agent mode reasoning. Requires is_agent_mode. Send content (no file). Returns data[], agent_data, and log_id. If source verification is enabled on the schema, fields are {value, source}. POST /agent/txt-json.
• claix.agent.audio — Run audio extraction plus Agent mode reasoning. Requires is_agent_mode. Returns data[], agent_data, and log_id from spoken content. If source verification is enabled on the schema, fields are {value, source}. Formats: MP3, WAV, M4A, OGG. Max 12 MB / 10 minutes.
• claix.window_context.get — Retrieve raw content and metadata from a persisted document (GET /get-document/{document_id}). Requires document_id from an extraction with window_context. Returns success, document_id, file_name, schema_id, processed_at, and content. Free call.
• claix.window_context.ask — Ask up to 5 typed questions about a persisted document (POST /document-context/{document_id}). Requires document_id from an extraction with window_context. Each item is { question, format } where format is string|int|boolean|timestamp|array; question max 400 characters. Returns user_ask (echoed with format), typed ia_response, and log_id (null if not in the document). If source verification is enabled on document queries, each ia_response item is {value, source} citing markdown evidence, or source is requires_human_revision.
• claix.spaces.create — Create a knowledge space to group persisted documents (POST /create-space). The only field is name. Returns space_id, name, and created_at. Pass that space_id as the optional space_id when extracting, then query the whole group with claix.space_context.ask. Free call.
• claix.spaces.delete — Delete a knowledge space owned by the API key (DELETE /delete-space/{space_id}). No body or query params. Returns { space_id } on success. Irreversible. Free call. 404 if the space does not exist or belongs to another account.
• claix.space_context.ask — Ask up to 5 typed questions across every document grouped in a knowledge space (POST /space-context/{space_id}). Same input and output as claix.window_context.ask: questions[] of { question, format } (format: string|int|boolean|timestamp|array), but the answer is built by cross-referencing all the documents in the space instead of a single one, so use it to compare, add up, or reconcile data spread over several files. Requires space_id, the same one passed as the optional space_id when extracting. Question max 400 characters. Returns user_ask, typed ia_response, and log_id (null if the answer is in none of the documents). If source verification is enabled on knowledge space queries, each ia_response item is {value, source} naming document_id and file_name.
• claix.document.delete — Delete a persisted document by document_id (DELETE /delete-document/{document_id}). No body or query params. Returns { document_id } on success. Irreversible. Free call. 404 if the document does not exist, is foreign, or was already purged.
• claix.document.replace — Replace the content of a persisted document with another document's content (POST /replace-document). Body: document_id (kept) and new_content_document_id (source, deleted after copy). Records a swap, bumps version, and returns swap_id, version, and swaps_count. Free call.
• claix.spaces.add_document — Assign a knowledge space to a persisted document that has no space_id yet (POST /add-space). Requires document_id and space_id. Fails with 400 if the document already belongs to a space — call claix.spaces.remove_document first. Returns document_id, space_id, space_name, file_name, and version. Free call.
• claix.spaces.remove_document — Detach a persisted document from its knowledge space (DELETE /remove-document-from-space/{document_id}). Sets espacio_id to null so the document becomes unassigned. Fails with 400 if it had no space. Returns document_id, previous_space_id, and version. Free call.

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.

Work with this as data

Every MCP server here is available over the APIs.io API and to AI agents over MCP.

curl "https://apis.io/api/v1/mcp/claix"

curl "https://apis.io/api/v1/mcp?limit=25"