"Finding MCP servers that support SSE or Streamable HTTP, excluding stdio transport" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Chartbrew connects databases and APIs to dashboards and reports. Its official MCP server lets AI assistants find dashboards and datasets, read chart results, explore supported data sources, and create datasets and chart previews. Connect directly to the hosted server with OAuth or a Chartbrew API key. Access follows your Chartbrew team, role, and approved permissions. Review chart previews in Chartbrew before adding them to a dashboard. No local installation is required.
Ask your PostgreSQL, MySQL or Odoo data in plain words from Claude, ChatGPT or any MCP app. Read-only: STYD runs safe queries and answers with the real number, the period and the definition it used. No SQL needed. OAuth sign-in, sample data to try right away, and every answer names its workspace so data from different companies is never mixed.
Database schema inference, dialect normalization, query plan optimization, and SQL audit over streamable HTTP.
Check an Australian vehicle for open safety recalls by VIN. The index mirrors the federal vehicle recall register: 5,587 notices and 8.8 million VINs, refreshed hourly. Look up one VIN, check a batch, search by make and model, or read the full notice. Free, read-only, no authentication.
Turn Microsoft Fabric tables into an explainable graph and a GraphQL API. Understand how your Fabric tables fit together. See how your Fabric tables connect: the keys and relationships Krusgraph suggests, why, and what your data says, before a report or an app depends on them. A one-stop-shop for Data Engineering on Fabric
Data Oil is a multi-model database built for object storage. It uses a log-structured storage engine, snapshot isolation with optimistic commit, and a change feed from the write-ahead log. Its SQL dialect supports joins, window functions, CTEs, set operations, graph traversal and pattern matching. It has its own HNSW vector index and BM25 full-text index, and a write is searchable by keyword and vector as soon as it commits. Access is over HTTP, the PostgreSQL wire protocol (extended protocol). We have a founder's program available for projects which may be of interest https://dataoil.tech/founders.html if your interested lets chat ;)
Every spreadsheet is a table: upload Excel, CSV, Parquet or JSON files and query them in SQL (Apache DataFusion), with joins across formats, schema and column statistics. Hosted tableski server; connect with your tableski.io access token. Open source: github.com/yarenty/tableski
Exact, shared memory for multiple AI agents. Azquo is a hierarchical database: each fact is stored once in hierarchies that always total correctly, every write is attributed to the agent and person behind it, and any figure can be traced back to the file and cell it came from. There is no schema to design first - agents build and reorganise the structure themselves - and people work with the same data live in Microsoft Excel. Suited to finance and insurance work, where figures must stand up to review.
ParseHub.dev is a hosted document-to-records service with a remote MCP server. Agents can upload a CSV, PDF, or Word file, summarize and analyze CSV data (filter, sort, group_by, and more), read text from PDF and Word files, extract attendees, agenda items, and action items from meeting notes, ask a question about an uploaded document, and store files as database records to list and read later. Each account sees only its own files and records. **Endpoint:** `https://parsehub.dev/mcp` (Streamable HTTP, stateless) **Auth:** API key in the `X-API-Key` header (keys start with `mcp_`), or `Authorization: Bearer <API key or JWT>`. Every request without credentials returns 401. **Plans:** Free (100 API requests/month, 1 document upload), or 5,000 requests/month on the $9/month or $42/year plan. Every MCP request counts toward the allowance. **Tools:** upload_csv, summarize_csv, analyze_csv, upload_document, read_document, extract_meeting_notes, ask_document, database_status, list_database_documents, get_database_document, store_document, extract_stored_meeting_notes, export_database (administrators only). Not affiliated with ParseHub (parsehub.com), the web-scraping tool. ParseHub.dev does not scrape websites. By Poietes LLC. Docs: https://parsehub.dev/guide#connect-via-mcp
A calorie MCP that looks up calories and macros from a 4M+ food catalog, not model guesses.
It connects with Smart Data models database with more than 1000 open licensed data models and helps you to create applications and systems interoperable with existing standards or real applications
Connect your AI to any database — PostgreSQL, MySQL, or SQL Server — in seconds.
Persistent knowledge graph for AI-augmented teams. Store decisions, findings, and standing rules across agent sessions with semantic search and typed connections. Includes cross-session memory, audit trail, workspace isolation, and secret detection. Built for teams running agents that need to remember. Free until launch with team tier as default, anon trial available.
Build, validate, deploy — HTTP APIs, cron jobs, webhooks and MCP tools — from your AI client. Air Pipe MCP token as a bearer credential, e.g. 'Authorization: Bearer <token>'. Create one at https://app.airpipe.io/
PeeringDB MCP — the peering ecosystem database. Look up networks by name or ASN, find internet…
Living documents and tables that people and AI agents read, improve and create together. No sign-up.
Look up any Canadian drug product by brand name or DIN. Free drug_search tool.
Is a food, country or company in Japan MHLW imported food inspection orders? Rows as published.
Is this drug's shipment normal, limited or suspended in Japan (MHLW)? Hosted, history kept.
Push CSV, TSV, JSON, JSONL or Parquet from your agent and get a link a human can explore: filters, column charts, SQL, pinned findings and what changed since the last push. Viewing is free, no signup; anonymous datasets live 7 days. Tools: push, pin_finding, get_dataset, list_datasets, delete_dataset, get_limits. Docs: https://rows.page/docs/mcp
Bags That Pay: the site's own MCP server — dataset, enquiry, entities, listing (enquiry = a...
Deterministic safety, correctness & cost gate that vets Postgres SQL before your AI agent runs it.
A unified biomedical graph database that integrates 50+ primary data sources — genes, proteins, compounds, diseases, pathways, and clinical data — into a single queryable graph with billions of cross-reference edges. Its native MCP server gives LLMs direct access to structured, authoritative biomedical data, complementing their reasoning with reliable identifiers and up-to-date database content.
The BigQuery remote MCP server is a fully managed service that uses the Model Context Protocol to connect AI applications and LLMs to BigQuery data sources. It provides secure, standardized tools for AI agents to list datasets and tables, retrieve schemas, generate and execute SQL queries through natural language, and analyze data—enabling direct access to enterprise analytics data without requiring manual SQL coding.
PolicyTrak's MCP server lets an assistant read, and with permission update, an organization's location compliance records: locations, compliance fields, tabs and evidence files. Find fields expiring in the next 30 days, summarize missing evidence by location, or mark an inspection complete. Each connection is scoped to one organization; write access is opt-in and admins can require approval for every change.
Query your CSVs and Google Sheets from any AI agent. Upload a file or pick a sheet, then filter, group and total the rows with exact results. OAuth sign-in, read-only, hosted in the EU.
Query records, run reports and formulas, and insert or update records in Quickbase.
Save and find clothes you own in a digital closet. Add clothing descriptions or photos, search saved wardrobe text, remove selected garments, and get a private link to continue in Shopbots. Hosted by Tolstoy. Uses OAuth with PKCE and dynamic client registration; no paid account required. Shopbots linking requires separate sign-in and confirmation. Removing a garment deletes its closet record; copied photos are currently retained.
Anomaly AI is an AI data analyst for large datasets and spreadsheets. Its remote MCP server lets Claude Code or another MCP client with OAuth ask Anomaly about your Excel, CSV, GA4, database and warehouse data. Anomaly runs the analysis and replies in plain text with dashboard links, file downloads and chart images. MCP OAuth sign-in, no API key. Needs an Anomaly account.
Connect Karma.Domains to ChatGPT, Claude, Cursor, VS Code, or another MCP client — and find a domain in plain language. The same auctions, expired, backorder, and buy-now data you use in the app, plus saved filters, notes and tags, guest share links, and SEO enrich — all from chat.
