"Step-by-step guide to breaking down a request into parts" matching MCP servers:

Enables pushing enriched leads into Instantly or Smartlead campaigns with ICP score gating, deduplication, and dry-run previews via an Apify actor.

Resolves a company domain to its LinkedIn company page URL. Lightweight enrichment tool for sales and prospecting workflows.

MCP server for qualifying and responding to inbound leads in seconds using a multi-agent AI pipeline.

MCP server for STEPhie tools, providing secure access to publisher data and ad forecasting via Monday.com and Google Ad Manager.

A Model Context Protocol (MCP) server that connects LLMs to the Zendesk Support & Help Center APIs — with per-user OAuth 2.1 PKCE authentication and fine-grained tool visibility controls.

Connects Claude to Jobber to manage clients, jobs, invoices, quotes, and scheduling through natural language.

Enables AI assistants to manage Bitrix24 CRM entities, tasks, project kanban boards, and Scrum sprints through an incoming webhook, requiring explicit user confirmation for all write operations.

An MCP server that bridges AI agents to the eyeot ERP, exposing ~600 business actions (CRM, sales, stock, HR, finance, etc.) as MCP tools over stdio via OAuth 2.1 authentication.

A read-only MCP server that connects to HubSpot to audit CRM data, diagnose RevOps maturity, identify at-risk deals, and provide step-by-step guidance for fixing issues.

Read-only MCP server for the Ploomes CRM API, providing 49 tools to query contacts, deals, products, and other business data using natural language.

Provides read-only access to the Planning Center People API, enabling natural language queries for people, households, background checks, and lists.

MCP server that enables Google ADK agents to triage solar fault signals, retrieve Salesforce diagnostics via hosted MCP prompt templates, and create WorkOrder records when replacements are needed.

Enables read-only access to InvoiceNinja data, including invoices, expenses, clients, and tax reports, for AI assistants like Claude.

Enables AI assistants to discover and invoke Vremly API operations through a search-describe-request pattern, allowing them to view and manage shoots, customers, media, and invoices according to API key permissions.

Japanese SMB SaaS connectors for MCP. Includes an L-Step (LINE marketing automation) server exposing 19 tools for friends, tags, and messaging.

Enables Polish-speaking users to connect EstiCRM with MCP clients like Codex, Claude Code, and Claude Desktop, providing read-only operations by default with optional write tools, data masking, argument validation, and safe request handling.

Enables Claude or any MCP client to read, create, and edit GoHighLevel workflows through a logged-in Chrome session, with no API key or marketplace app install. Provides 30 tools for workflow CRUD and publishing, step-level patches, folder management, and location data such as tags, users, pipelines, and custom fields.

Enables turning a short description of a client's request into a priced draft proposal, with deterministic in-code pricing and a review link, from Claude, Cursor, Gemini CLI or any MCP client. Also lets users check a proposal's draft/viewed/accepted status, list recent proposals, and see their remaining proposal credits.

A unified MCP server that connects HubSpot, Clay, Apollo, Slack, and email to enable AI agents to execute multi-step GTM workflows such as prospecting, enrichment, CRM updates, and notifications.

Enables agents and CLI users to read ManyChat subscriber, tag, custom-field, flow, and page data and to request policy-checked messaging actions, with a fail-closed Meta messaging-policy guard that blocks sends lacking trusted channel evidence.

Enables a desktop AI agent to read from and write to a single Halaxy practice account, turning intake material like referral PDFs, emails and form photos into patient, referrer and referral records, and checking availability and booking appointments. Every write is gated by a prepare/approve/commit flow with duplicate checks, masking and read-only mode.

Gives AI agents access to five MSP products' APIs — Core, Lifecycle Manager, ControlMap, Backup Radar and Quoter — through 381 tools that read clients, contacts, assets, tickets, roadmaps, compliance data, backup health and quotes, and on explicit request create, update, attach, publish or delete records using a single API key passed per request.

Enables AI agents to read service desk tickets, time entries, client accounts, contacts, contracts and the service catalog, and on explicit request create tickets and add ticket notes, through the Kaseya BMS REST API v2. Stateless and multi-tenant, it takes credentials per request via HTTP headers and returns structured JSON results or error envelopes.

Enables AI agents to retrieve a service provider's profile, submit bounded quote requests for human review, and check request status through MCP tools.

Enables AI agents to search and read tickets and their conversations, contacts, companies, agents, groups, knowledge base articles, SLA policies, business hours and canned responses, and, on explicit request, create and update records, reply to tickets, add notes, and perform confirmed deletes, merges or conversions. It is stateless and multi-tenant, taking per-request credentials via HTTP headers so every action is performed as the designated agent.

Enables authorized users to query platform data, request analyses, and perform business operations in natural language from Claude and Codex, using OAuth login tied to the Resgata.ai admin account. It is currently under construction, with only a local synthetic-data demo available.

Enables an AI agent to discover the objects and fields of a Salesforce org, run SOQL queries and SOSL searches, and, on explicit request, insert, update, upsert, or delete records through the REST API. Credentials are supplied per request as HTTP headers and never stored, so a single deployment serves multiple orgs.

Turns a recruitment database into an AI-queryable pipeline, enabling natural language queries to search contractors, build shortlists, draft outreach, and book engagements.

Enables AI agents to work in HaloPSA by listing, creating, and updating tickets and ticket notes, clients, sites, contacts, assets, agents and teams, invoices, and the reference tables needed to write tickets correctly. Credentials are supplied per request and nothing is stored between calls.

Enables an AI assistant to operate an academy hub through its authenticated internal API, covering cohorts and sessions, instructors, courses and media, CRM leads, drip email, memberships, and venue events. All writes are two-step: a dry run returns a preview of the exact change, which must be confirmed to commit.