Skip to main content
Glama

Related Servers

Alternatives to Civ6 MCP CN

No user-submitted related servers found.

    Related Servers

    • A
      license
      A
      quality
      C
      maintenance
      Enables MCP-compatible AI agents to play full Civilization VI games by reading game state and issuing rule-enforced actions such as moving units, managing cities, conducting diplomacy, and ending turns.
      76
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      An MCP server that lets LLM agents play full games of Civilization VI. It connects to a running game and provides tools for unit movement, city management, diplomacy, and more, all through the game's rule-enforcing APIs.
      76
      230
      MIT
    • F
      license
      A
      quality
      B
      maintenance
      Enables an AI coach to inspect Civilization VI game state, check game connectivity, and query detailed rules for techs, civics, units, districts, and more through MCP tools.
      8
      -
    • A
      license
      A
      quality
      B
      maintenance
      Enables any local AI agent to play turn-based games over MCP by exposing reset, observe, and act verbs with structured observations and validated legal actions.
      6
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables an MCP agent to observe and command Slay the Spire 2 game state via HTTP, and optionally autopilot combat with a local deterministic policy, without LLM in the critical path.
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      MCP server that acts as a local stdio adapter for Civarium agent HTTP APIs, enabling interaction with game agents through tools like get_active_round, get_visible_state, submit_command, list_my_commands, and wait_next_round.
      15
      MIT

    TDQS

    A3.6/5.0

    Scored across 99 tools

    Disambiguation3/5

    Most tools map to a single engine action, but several clusters overlap: five save/recovery tools (load_save, load_game_save, load_save_from_menu, restart_and_load, list_saves) and a dense advisory layer (get_settle_advisor vs get_global_settle_advisor vs assess_settle_location; get_strategy_notes vs get_expert_playbook; assess_attack vs suggest_siege_plan) force the agent to parse long descriptions to pick correctly. The descriptions do carry disambiguating guidance in most cases, which keeps this above a 2.

    Naming Consistency4/5

    Nearly everything is snake_case with a verb prefix (get_/set_/choose_/propose_/assess_/promote_), including the paired get_x / do_x pattern for advisors. Minor deviations are noun-first names like plan_list/plan_add/plan_done/plan_drop and action-dispatchers city_action/unit_action/spy_action, but the scheme stays readable and predictable.

    Tool Count2/5

    99 tools is far past the point where an agent can hold the surface in context; the dispatcher tools (unit_action, spy_action, city_action, propose_trade, run_lua) already absorb many variants, so the remaining count is inflated. The domain (a full 4X game) explains some breadth, but sub-tool proliferation in advice, memory, and save/load makes it heavy rather than well-scoped.

    Completeness4/5

    Coverage is unusually broad: map/units/cities/production/queues, tech+civics, religion, governors, great people, spies, trade routes, World Congress, victory tracking, save/load recovery, and persistent memory all have tools. Minor gaps exist (no great-work/tourism management, limited city-state quest handling, tile-level map queries capped by radius), but nothing that would dead-end a core workflow.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues