
Remote MCP server for DocQuery: query a spreadsheet and its PDFs together as linked tables
Remote MCP server for DocQuery: query a spreadsheet and its PDFs together as linked tables (Claude, Cursor, Cline)
·
Remote MCP server for DocQuery. Point Claude, Cursor, Cline or any MCP client at a spreadsheet (Excel, CSV, Google Sheets, Airtable) and the PDFs that belong to it (invoices, contracts), and query them together as linked relational tables. Every extracted row keeps its source file (and page where known) so the agent can cite the PDF.
This repository holds the public connection details and client configs. The server itself is hosted; there is nothing to install or run locally.
https://docquery.io/api/v1/mcp (Streamable HTTP)Authorization: Bearer <key>dq_demo_readonly (sample customers + invoices workspace)io.docquery/docquery| Tool | What it does |
|---|---|
list_tables | Tables in the workspace with their columns |
list_relations | Foreign-key links between tables (e.g. invoices -> customers) |
query_table | Rows from one table, with filter, search, columns projection, limit/offset |
related_rows | Follow a relation from one row to its linked rows |
MCP access is read-only on purpose; edits happen in the DocQuery app or the REST API.
{
"mcpServers": {
"docquery": {
"type": "streamableHttp",
"url": "https://docquery.io/api/v1/mcp",
"headers": { "Authorization": "Bearer dq_demo_readonly" }
}
}
}Some clients use "type": "http" instead of "streamableHttp". Replace dq_demo_readonly with your own key from your workspace in https://docquery.io to query your own data. Clients that support OAuth can omit the header and sign in.
This repo is also a Cursor plugin (.cursor-plugin/plugin.json + mcp.json). It connects to https://docquery.io/api/v1/mcp with no stored secret: Cursor signs you in to DocQuery with OAuth (read-only scope mcp:read) the first time a tool is used.
gemini extensions install https://github.com/acrogenesis/docquery-mcpConnects to https://docquery.io/api/v1/mcp; Gemini CLI signs you in with OAuth on first use.
claude mcp add --transport http docquery https://docquery.io/api/v1/mcp \
--header "Authorization: Bearer dq_demo_readonly"curl -s https://docquery.io/api/v1/mcp \
-H 'Content-Type: application/json' \
-H 'Accept: application/json, text/event-stream' \
-H 'Authorization: Bearer dq_demo_readonly' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'Free: 5 documents, 10,000 rows, REST + GraphQL + MCP. Starter $29/mo, Pro $79/mo. See https://docquery.io.
[email protected] · security reports: [email protected]
Built by Adrian Rangel (@acrogenesis).
Pick your client and paste the snippet. Each one is the same server, written the way that client expects it.
claude mcp add docquery --transport http https://docquery.io/api/v1/mcp{
"mcpServers": {
"docquery": {
"url": "https://docquery.io/api/v1/mcp",
"type": "streamableHttp",
"headers": {
"Authorization": ""
}
}
}
}code --add-mcp '{"name":"docquery","url":"https://docquery.io/api/v1/mcp","type":"streamableHttp","headers":{"Authorization":""}}'Runs as a hosted service. Your client connects over the network and nothing is installed locally.
Paste this prompt into your agent. It reads this page and does the setup for you.
Read https://aiagentslisting.com/mcp/docquery-mcp-server to learn what the "DocQuery MCP server" MCP server does and how to install it. Add it to my coding agent's MCP configuration as documented on that page, then confirm the server connects and list the tools it exposes.Agents can also browse this directory over MCP at https://aiagentslisting.com/api/mcp
claude mcp add --transport http docquery https://docquery.io/api/v1/mcp| Name | What it does |
|---|---|
list_tables | List all tables in the workspace. Call this first to learn table and column slugs. Returns slug, name, row_count, and columns (slug, name, type, primary_key) for each table. Document-extracted tables |
list_relations | List the relations (foreign keys) between tables in the workspace. Each relation has from and to as "table_slug.column_slug" and a kind. Use it to find which columns link two tables before calling rel |
query_table | Read rows from a table. Optional filter is an exact-match map of column slug => value; optional search is a case-insensitive substring match across all cells. Returns source_document for the table (nu |
related_rows | Follow a relation from a source table to the rows it links to. Given a column on `table_slug` that participates in a relation and a `value` (usually a cell from a source row), returns the matching row |
| Name | What it does |
|---|---|
schema_overview | Summarize the workspace's tables, columns, and relations. |
find_rows | Find rows in a table matching a column value. |
count_by | Group rows of a table by a column and return counts. |
Read live from the server on November 15, 2026.
Maintain this server? Claiming proves you own the listing and earns the last 4 points.
Claim this listingPaste this line near the top of your repository's README. The badge always renders the current score.
[](https://aiagentslisting.com/mcp/docquery-mcp-server)Nothing comparable is listed yet.
No tagged releases on record.
Connect to the AI Agents Listing MCP server at https://aiagentslisting.com/api/mcp using the HTTP transport and complete the sign-in when it asks. Then call the submit_review tool for the listing "docquery-mcp-server" with a rating from 1 to 5 and a short note on what worked and what did not.No reviews yet
Be the first to share your experience with this tool.
One email a week. New agents, MCP servers and skills, and what is actually getting traction.