Skip to main content
Glama
office233

free-coding-agent

by office233
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

Related Servers

Alternatives to free-coding-agent

No user-submitted related servers found.

    Related Servers

    • Keshro MCP

      jlewitt1
      A
      license
      D
      quality
      C
      maintenance
      The intelligent execution layer for coding agents, exposed as an MCP server for high-stakes engineering projects. It enables AI agents to manage plans, tasks, and integrations via tool calls.
      25
      MIT

    • Free Codin Agent

      office233
      A
      license
      C
      quality
      F
      maintenance
      This MCP server gives an AI coding host controlled, client-agnostic access to a local machine's developer capabilities: transactional file edits, shell and PTY execution, Git and project inspection, language-server operations, isolated browser automation, Windows UI automation, VS Code state, durable jobs, and checkpoints, all bounded by filesystem root allowlisting and resource admission controls. It speaks standard MCP over stdio, Streamable HTTP, and legacy HTTP+SSE, and can also run headless as a long-lived job runner without any hosted model vendor.
      114
      ISC

    • rvn

      valrinx
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables AI clients to securely control and interact with a local Windows machine through 218 configurable tools for files, Git, processes, Windows UI, browser automation, WSL, Office, recovery, skills, and child MCP servers.
      11 npm
      MIT

    • Workspace MCP

      pira73br
      F
      license
      Not graded
      quality
      D
      maintenance
      Secure local development platform that exposes controlled developer capabilities (FS, Git, search, command execution) to AI assistants via MCP with deny-by-default security and audit logging.
      -

    • my-pi

      BoxBoxmari
      A
      license
      C
      quality
      B
      maintenance
      Local-first MCP runtime for coding agents with bounded workspace access, content-preconditioned writes, AST search, LSP navigation and diagnostics, and Git status/diff. Designed to give coding agents useful repository access without treating unrestricted shell access as the default integration boundary.
      2
      13
      2
      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

    C2.9/5.0

    Scored across 128 tools

    Disambiguation2/5

    Several large tool clusters overlap heavily: run_command/process_start/pty_start/job_start all run or manage commands, chrome_* and browser_* duplicate browser automation, and lsp_* and vscode_* duplicate language-server queries. Descriptions distinguish some contexts (real Chrome vs Playwright, background process vs PTY vs durable job), but an agent could easily misselect among them.

    Naming Consistency4/5

    The dominant convention is snake_case with consistent domain prefixes (browser_, chrome_, process_, task_, lsp_, vscode_), which makes the set mostly predictable. Minor deviations exist, such as list_processes vs process_list, get_system_info, file_info, record_clip, batch, and run_command, preventing a perfect consistency score.

    Tool Count1/5

    128 tools is an extreme over-provisioning for a single coding-agent server. Even with broad ambitions, the surface is far beyond the typical 3-15 well-scoped range and directly contributes to selection ambiguity and maintenance overhead.

    Completeness4/5

    The server covers a remarkably broad coding-agent lifecycle: file read/write/patch/edit, search, git status/diff/log/commit, shell, process/job/PTY control, LSP diagnostics and navigation, browser and real-Chrome automation, Windows UI automation, durable tasks, checkpoints, and web access. Some common operations are missing or only reachable via shell, such as advanced git workflows (push/pull/branch/PR) and project scaffolding, so it is strong but not fully complete.

    Maintenance

    ActivityNo data
    ResponsivenessNo issues

    Resources