50 tools and 400 functions for working with Excel/.xlsx spreadsheets — read/write, recalculate formulas, diff, repair broken references, and audit. Built for AI agents.
Enables agents to transform tabular Markdown content into structured, type-inferred records with normalized formatting through an MCP-compatible interface.
Lets an AI agent pull the user's own Douyin creator-backend work data — plays, likes, comments, shares, saves, 5-second completion rate and more — into a locally accumulating CSV plus a daily overview, with tools for status checks, fetching, merging, and retrospective analysis. Access is read-only to the user's own account, needs no third-party dependencies, and keeps all data on the local machine.
Enables AI agents to convert CSV text into JSON arrays with automatic delimiter detection and optional header-row handling, accessed through a pay-per-call x402 micropayment API.
Enables agents to reconcile piping material take-offs against Plant 3D SCSA exports by previewing diffs and applying quantity corrections, insertions, and gated removals with dry-run and explicit confirmation flags.
A stdio MCP server exposing a validate_emails tool that lets agents screen email lists without sending mail or probing SMTP, checking syntax, DNS/MX records, disposable domains, role accounts, free providers, typo suggestions, and SPF/DMARC. Each address comes back with a valid/risky/invalid/unknown verdict plus machine-readable reason codes so agents can clean leads and signups before outreach or import.
Give your AI agent the entire China A-share market: 55 datasets of prices, financials, capital flows, corporate events and futures/options, stored locally and queryable with read-only SQL. Built point-in-time with delisted stocks kept, so backtests don't lie — no account, no API key.
MCP server that diagnoses Apache Spark job failures and optimizes performance using stack-trace analysis and LLM providers, supporting EMR and local sources.
Enables users to convert a vendor partner directory (such as PartnerPage or the Shopify Partner Directory) or a trade body member list into one company row per listing, each carrying website, domain, tier, tags, and location for Clay-ready output. It runs the extraction on Apify, returning dataset rows for up to 20 directory URLs with optional deduping, detail enrichment, and a cost cap.
Enables an AI assistant to reliably read and chunk PDF/text documents, validate extracted JSON against a schema with full error paths, and save structured output—all confined to a single allowed directory.
Enables looking up mobile phone numbers for a list of contacts by chaining your own Prospeo, Lusha, ContactOut, and FullEnrich keys until a provider returns a number. Returns one row per contact with the number in E.164 format, line type, country, a Do Not Call flag where reported, and the provider credits spent.
Enables AI assistants to list, describe, profile, sample, and run read-only SQL over local CSV, Parquet, and JSON files confined to user-approved folders. Queries are sandboxed with row caps, timeouts, and blocked write/DDL statements for safe by-default access.
MCP server exposing Apache Airflow REST API operations as tools — list DAGs, inspect runs and task instances, trigger DAG runs, and check failed DAGs and
scheduler health
Enables an AI client to track a watch list of contacts and retrieve only what changed since the last run — departures, new employers, replacements, and new hires after a role closed — each row carrying match evidence, source dates, and ready-to-use outreach payloads. It runs the analysis on Apify using the caller's own provider keys, supports stored or caller-held state, and can push results to a signed webhook.
Enables an AI assistant to answer customer-success questions by synthesizing simulated billing, support ticket, and product usage data into composite churn-risk scores, bands, and plain-language explanations for fictional accounts. It exposes raw-data tools, a synthesis tool, and a methodology resource so users can list at-risk accounts or get a per-account health summary.
Commercial intelligence gateway for 500 US franchise restaurant chains, 210,000+ store locations, POS hardware fingerprints, and statutory FDD Item 19 unit economics.
Enables AI assistants to inspect, update, and health-check a local Qlib China A-share dataset, retrieve daily prices for up to 20 symbols, and list index pool members on a given date. It runs locally over stdio so the dataset stays on the user's machine.
Unified MCP server for Arpe.io data tools enabling AI assistants to build, preview, and execute high-performance data commands including database export, transfer, pipeline, and migration.
Coupler.io MCP server lets AI assistants query business data from 400+ apps in natural language. The data is blended and kept up to date by Coupler.io, a reporting automation platform for business teams.
Enables parallel tagging and classification of CSV data using multiple LLM providers with structured output, confidence scores, and optional reasoning for batch classification tasks.
A Model Context Protocol (MCP) server that enables MCP clients like Claude Desktop to interact with protocols.io, a popular platform for sharing scientific protocols and methods.
Data compression MCP server with auto-algorithm selection (gzip, brotli, deflate). 7 tools for compress, decompress, analyze, store, retrieve, list, and stats. Achieves 60x compression on docs, 30x on SQL. Lossless round-trip verified. Zero dependencies.
A meta-layer MCP server that treats connectors as objects and access paths as morphisms, enabling automated coherence checks across multiple data sources to detect inconsistencies. It provides tools to list sources, compare fingerprints for coherence, and identify divergent or unreachable sources.
Enables Claude to inspect and operate Apache Airflow over its REST API, providing read tools and safe write operations (gated by read-only mode) for managing DAGs, runs, tasks, and pools.
Enables AI agents to list metrics and dimensions, inspect definitions, and run governed metric queries against Apache Iceberg tables through a semantic layer, without writing SQL or accessing raw rows or columns outside their role.
An MCP server that exposes Akahu (New Zealand open-banking) data to LLM agents, allowing them to list bank accounts, inspect investment holdings, and pull transactions for analysis.
A tutorial implementation MCP server that enables analysis of CSV and Parquet files. Allows users to summarize data and query file information through natural language interactions.
An MCP server that connects Claude and other MCP clients to Microsoft Power BI via its REST API using a Service Principal, enabling natural language queries to list workspaces, run DAX queries, refresh datasets, and explore reports.
Institutional-grade zero-lookahead Technical Analysis scanner with quantitative confluence scoring & native Model Context Protocol (MCP) server for AI trading agents.
Enables an AI assistant to query and browse multiple database engines read-only, with the ability to switch connections and engines dynamically during a session.
Enables AI agents to discover and query data federated across MySQL/MariaDB, PostgreSQL, ClickHouse, S3 and Kafka with SQL, exposing tools to list databases, schemas, tables and connections, describe columns, search objects, inspect table statistics, run EXPLAIN, and execute arbitrary statements. It runs locally over stdio against a PostgreSQL-wire endpoint and returns structured results or SQLSTATE-coded errors.
Gives Claude read-only tools to list leads, inspect normalized business context, preview the deterministic routing decision (including a country inferred from untrusted notes, always flagged for review), inspect a case's ledger state and audit trail, and explain the ordered policy rules. All outputs are read-only, so the assistant can explain why a lead went where it did while every assignment still requires human approval.
Deterministic MCP server for civil engineering, roadworks, utilities, 3D TIN earthworks, and construction Bill of Quantities (BoQ) auditing across CAD drawings (.dxf/.dwg/.pdf) and Excel spreadsheets (.xlsx). Provides 17 specialized tools combining exact Shapely 2.0/GEOS computational geometry, precast manhole optimization (DIN EN 1917 / ASTM C478), and non-destructive Decimal spreadsheet formula
Read-only-by-default MCP server for Datanika, an open-source dlt + dbt-core data pipeline platform: browse connections, introspect and preview source tables, compile and run dbt transformations, and monitor pipeline runs. 25 tools (17 read-only, plus 8 write tools gated behind --allow-write); source lives in the datanika-mcp/ subdirectory of the repo.
A read-only MCP server that lets an assistant search the public SDCStudio catalog, describe a published Semantic Data Charter model, list its leaves and enumerated codes, verify a package directory's integrity, and read a Governed Data Record against its model. Models come from the host fixed at startup or from a local package directory, with no account required.
A small Python MCP server that lets Cursor's agent browse databases and tables, inspect columns, run read-only SQL, and register new sources or cache tables against a Zetaris instance. It is paired with a project rule that steers the agent to do all its data work through this server rather than going around it.
Minimalistic MCP server that lets AI assistants inspect, quality-check, and clean CSV datasets through tools, resources, and prompts, without needing local file access.
An MCP server that exposes Estuary Flow pipeline operations as typed tools, enabling agents to inspect pipeline health, publish captures and materializations, edit/restart tasks, and read landed documents via tool calls.
MCP server for the BAIC Data Layer. Provides tools to manage sources, knowledge bases, knowledge clusters, run data agents, and create/manage pipelines.
Enables agents to interact with MySQL databases securely, supporting multi-database read-only queries, protected DML writes, and streaming exports to Sandbox Datasets.
Read-only MCP server that exposes the Automic Registry Platform API, letting users query issuers, securities, daily prices, top holders, and distributions, and run asynchronous registration, transaction, and fund cash flow reports. Report and payment list outputs are saved to a local directory with restricted permissions, with small results returned inline.
A Model Context Protocol server that allows interaction with the RubyGems.org API to fetch metadata about Ruby packages, search gems, and explore dependencies and ownership information.
Enables read-only access to FileMaker databases through the Data API, allowing users to retrieve records, analyze metadata, search across layouts, and infer relationships while maintaining data security.
A server that connects to PostgreSQL databases and provides tools for safely exploring schemas, running read-only SQL queries, and performing data analysis with pre-built templates.
Enables exhaustive combinatorial search over a discrete space by enumerating the full Cartesian product, sharding work across accelerators, scoring every combination against a named objective, and returning a ranked list, with cost planning and emergency stop controls.
Enables AI agents to interact with Microsoft Fabric by exposing tools for managing workspaces, notebooks, SQL queries, pipelines, and Livy Spark sessions. It provides a comprehensive set of operations for data engineering and analytics tasks using standard Azure authentication.
Enables offline-first alpha research by providing a local stdio interface to query run status and reports, list approved method cards, execute replay runs, and stop runs, all without any submission capability.