"SearXNG, a privacy-respecting metasearch engine" matching MCP servers:

A provably read-only SQL layer for AI agents (MCP) and weekly reports — over the database behind an ERP (Logo Tiger, Netsis, Mikro). Statement-checking guard, measured against 28 attacks.

MCP server for Dynamics 365 Finance & Operations certification prep, enabling interactive drills with accuracy tracking and review.

MCP server that enables Claude, ChatGPT, and other LLMs to interact with ERPNext sites through natural language, supporting document CRUD, search, reports, workflows, and custom tools, while respecting user permissions and logging all calls.

Provides authenticated, read-only access to SuperOps data via MCP, supporting stdio and HTTP transports with privacy-safe redaction.

Enables Gemini Enterprise and LLM agents to securely connect to and act on enterprise systems including Xero accounting, BigQuery, Firestore, and Sage HR, with OAuth 2.0 PKCE, privacy and cost guardrails, and an embedded admin portal.

MCP server that enables LLMs to interact with ERPNext/Frappe sites for document CRUD, search, reports, workflows, and analytics, respecting user permissions and logging all actions.

Enables read-only investigation of NOVA's Dolibarr accounting and commercial data through an AI assistant, with privacy protection and deterministic accounting rules.

MCP server for Lexware Office that enables querying and managing contacts, sales documents, vouchers, files, payments, and webhooks through a sandboxed two-tool interface (search/execute) with read-only-by-default write safety.

Enables AI to dynamically discover and invoke any Cin7 Core API endpoint using three generic tools (list, describe, invoke) plus a bug-report tool, covering the entire API surface without predefined endpoints.

Provides complete FreshBooks integration with 87 tools covering accounting, invoicing, time tracking, expense management, client/project management, and financial reporting through OAuth2 authentication.

Enables AP analysts to find out why an Oracle Fusion Cloud ERP invoice is not paying by pulling the invoice, its holds, accounting period status, and budgetary control results into one read-only answer with resolution steps and owning teams. It returns funds statuses and failure reasons, reporting a balance only when Oracle Budgetary Control supplies one and marking numeric fields unavailable otherwise.

A read-only MCP server that connects Claude Desktop to TallyPrime, enabling natural-language auditing and analysis of accounting data directly from the local Tally installation.

A read-only MCP server for Anaplan that exposes 5 tools for business users to explore data through an AI assistant, with session caching and metadata gating.

MCP server for ReAI, the Norwegian cloud accounting system, enabling AI agents to read books, look up accounts and VAT codes, and perform bookkeeping through a curated toolset with safety guardrails.

Exposes NetSuite saved search exports as a structured query interface for Claude, enabling file discovery, column inspection, filtering, aggregation, memo categorization, and anomaly detection.

MCP server that validates and writes DATEV-Format (EXTF) files: Buchungsstapel (booking batches) and Debitoren/Kreditoren (customer and supplier master data). Ask your AI assistant why DATEV rejected an import, or have it turn a list of bookings into a file DATEV accepts.

Lets an AI assistant read and write business records in plain language, including looking up people, creating and updating tasks, logging time, and pulling utilization reports through a synthetic ops platform or an optional ClickUp adapter.

MCP server that exposes the Timetta OData API as a universal query gateway, allowing users to list, describe, and query OData entities through natural language.

A read/write MCP server that connects AI assistants to the OpenEMIS school management system, allowing natural-language queries and write operations across 678 resources and 3361 endpoints.

MCP server for Oracle Fusion BI Publisher that lets AI agents run queries, reports, and manage catalog objects via a secure, scoped interface.

Enables AI agents to interact with Distru's ERP data through read tools and a guarded sales-order draft tool, using realistic fixture data by default or the live public API with an optional token. It provides dry-run writes bound to a confirmation token, JSONL audit logging, and a purchase-order matcher that flags catalog traps instead of guessing.

Lets an LLM explore a cryptic legacy ERP schema in plain language through a semantic layer (table listing, column descriptions, published dictionary) and run single read-only SELECT queries that return capped results. Enforces safety at the database engine level: only reads are authorized, sensitive columns are masked to NULL, queries are aborted after a few seconds, and every call is written to an append-only audit log.

A Node.js MCP server that provides tools for interacting with the Sienge API, covering modules like nucleus, cadastros, and compras with parity validation against the Python version.

Enables querying Odoo's model registry (fields, inheritance, methods) without a database connection by loading the registry in-memory.

Enables MCP-compatible AI agents to create and manage iCount accounting documents and clients directly from a conversation using a static API token.

Gives AI clients guarded access to SAP Business One over SAP HANA / MS SQL and the Service Layer OData API. SQL is read-only, enforced on the server; Service Layer is GET-only by default, with opt-in writes that require user approval unless a profile explicitly turns it off.

Enables MCP clients to work with Wave invoicing for a single business, including looking up customers and invoices, creating customers and draft invoices, and approving, sending, or recording payments behind a preview-then-confirm step.

Read-only MCP server that lets AI assistants query a locally running TallyPrime installation through its HTTP-XML gateway, exposing companies, ledgers, vouchers, trial balance, P&L, balance sheet, receivables, payables, and stock reports as clean typed JSON. All processing stays on the user's own machine, with no write access and no cloud backend.

Enables AI agents to investigate a legacy ERP's PostgreSQL database through read-only queries, apply writes and multi-statement atomic transactions behind static and in-transaction guardrails, and snapshot tables before destructive changes. Row limits, sequence-integrity checks, and optional JSON audit logging keep every call bounded, reversible, and traceable.

Enables an LLM agent to read from and propose changes to a financial ERP, executing writes only after human confirmation delivered through the channel, with role checks, risk tiers, audit logging, and a master kill-switch.