Skip to main content
Glama
chaojixiaoyezi

Agent Bridge

by chaojixiaoyezi
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to Agent Bridge

No user-submitted related servers found.

    Related Servers

    • agent-bridge

      itcomduke
      A
      license
      Not graded
      quality
      C
      maintenance
      An MCP central server that lets multiple AI agents (e.g., Claude Code, kimi-code) exchange private messages, shared channel broadcasts, and unified message streams via MCP tools, with SQLite persistence and per-connection identity binding.
      31 npm
      MIT

    • agent-bus-mcp

      MustaphaSteph
      A
      license
      Not graded
      quality
      D
      maintenance
      A local MCP server that connects AI coding agents (Claude Code, Codex, Cursor, etc.) on the same machine via a shared message bus, enabling them to chat, delegate tasks, and collaborate privately without cloud or internet.
      44 npm
      17
      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

    B3.4/5.0

    Scored across 14 tools

    Disambiguation4/5

    Most tools have clear, distinct purposes. The main overlap is between agent_send (which supports reply_to metadata) and agent_reply, both of which can send quoted messages; agent_reply additionally acknowledges the original. Other potentially similar tools (wait, notifications, history) are well-differentiated by their delivery modes.

    Naming Consistency3/5

    All tools share the consistent 'agent_' prefix, but the suffix pattern is mixed. Some use verb_noun (agent_update_profile, agent_create_room), some are bare verbs (agent_register, agent_send, agent_wait), while others are nouns (agent_following, agent_heartbeat, agent_history). This makes the naming less predictable than a purely verb_noun convention.

    Tool Count5/5

    14 tools fit well within the ideal 3-15 range for a focused domain. Each tool covers a distinct aspect of identity, presence, rooms, messaging, notifications, or social graph, without unnecessary redundancy. The count feels scoped and manageable for an agent to navigate.

    Completeness3/5

    The set covers core messaging, presence, and room creation, but has notable lifecycle gaps. There is no way to leave or delete a room, no tool to list joined rooms, and no way to join an existing room after the initial registration. Message editing or deletion is also missing, which could cause dead ends in workflows.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources