Skip to main content
Glama
Sign In
Joist MCP

Joist MCP

by cotlet-connect
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Related Servers

Alternatives to Joist MCP

No user-submitted related servers found.

    Related Servers

    • Joist MCP Server

      cotletdev
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents and scripts to access clients, estimates, invoices, payments, and reports from a user's own Joist account through their Chrome session, over MCP or a local REST API.
      135 PyPI
      5
      Elastic 2.0

    • invoice-simple-mcp

      cotlet-connect
      A
      license
      A
      quality
      C
      maintenance
      Connects an AI agent to a user's own signed-in Invoice Simple account so it can create, send, duplicate and chase invoices and estimates in plain language, including listing unpaid invoices by client, amount and due date. Runs as a hosted HTTP endpoint or a local stdio proxy, requiring no Invoice Simple API key.
      7
      Elastic 2.0

    • Tradify MCP server

      cotletdev
      A
      license
      A
      quality
      B
      maintenance
      Enables AI agents to read and change jobs, job status, customers, quotes with line items, invoices, quote and invoice email, payments, and Scheduler bookings in an account by reusing the user's own signed-in Chrome session, with no official API keys needed. Ships read-only hints and confirmation prompts for tools that reach other people, and can be run over stdio or streamable HTTP.
      2
      22
      403 PyPI
      6
      Elastic 2.0

    • RazorSync MCP

      cotlet-connect
      A
      license
      A
      quality
      C
      maintenance
      Lets AI agents work inside your own signed-in RazorSync account, so you can schedule and reassign jobs, create work orders, turn completed work into invoices, and follow up on unpaid bills using plain language. Works with Claude Code, ChatGPT, Cursor, and any MCP-capable agent, with a local stdio server that forwards tool calls to the hosted endpoint.
      7
      Elastic 2.0

    • Taskade MCP Server

      Jian9112
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables AI clients such as Claude, Cursor, VS Code, and Windsurf to manage workspaces, projects, tasks, and AI agents through natural language, using a hosted OAuth-authenticated endpoint or a local stdio package. It also ships an OpenAPI codegen tool for generating MCP tools from any OpenAPI spec.
      2,203 npm
      MIT

    • Taskade MCP Server

      Leone542
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables AI assistants like Claude, Cursor, VS Code, and Windsurf to manage workspaces, projects, tasks, and AI agents through natural language, with a hosted OAuth server or a local stdio package. Also supports generating MCP tools from any OpenAPI spec.
      2,203 npm
      MIT
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.6/5.0

    Scored across 7 tools

    Disambiguation4/5

    Each tool maps to a distinct step in a browser workflow (guide, status, open, read, click, type, close), so misselection risk is low. The only mild overlap is between joist_guide (instructions/screens) and joist_status (account and connection readiness), both described as first-call tools, which could cause a hesitant agent to pick the wrong one initially.

    Naming Consistency5/5

    All tools use the same joist_ prefix followed by a short, lowercase verb (guide, status, open, read, click, type, close). The pattern is predictable and readable throughout.

    Tool Count5/5

    Seven tools is a tight, well-scoped set for a browser-automation wrapper: one per primitive action plus onboarding/status helpers. No tool feels redundant or out of place.

    Completeness3/5

    The surface covers the core loop (open, read, click, type, close) plus onboarding, but generic browser primitives like selecting a dropdown option, pressing keys/Enter, scrolling, or waiting for page loads are absent. In Joist forms with dropdowns or multi-step flows, these gaps could create dead ends, though agents may work around some by clicking.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Resources