Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
ARK_API_KEYNoAPI key for Volcengine Ark models
ZAI_API_KEYNoAPI key for Zhipu GLM models
OPENAI_API_KEYNoAPI key for OpenAI models (e.g., gpt-5)
DEEPSEEK_API_KEYNoAPI key for DeepSeek models
ANTHROPIC_API_KEYNoAPI key for Anthropic models (e.g., claude-opus-4-8)
UNITY_PROJECT_ROOTYesRoot path of the Unity project

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
pingA

健康检查:确认 BrainRegion MCP server 可达。

mark_findingA

标记一条 finding 的采纳情况,写入 Review Memory,供下次 review 模型可信度加权。

finding_id/params_hash 从 review_document 返回取。未传 params_hash 时按 finding_id 反查最近含此 id 的 review(扫 consensus+majority+individual+deduped_ids)。 decision: accepted|rejected|partial。标记后默认失效该 review 缓存,下次同内容审查重算 reliability(该模型该维度按历史采纳率降/升权)。note 是 decision reason 自由文本。

mark_adviceA

标记一条外援 advice 是否有用,写入 Advice Memory。

advice_id/consultation_id 从 consult_problem 返回取。decision: accepted|rejected|partial|unknown。只记录最小反馈元数据和用户反馈文本,不保存原始 prompt、问题正文或 advice 全文。

record_experienceA

记录一条经验到 Experience Memory(append-only),供后续按关键词召回注入 consult context。

summary 必填;triggers 是召回关键词(词面命中);region 可空(全局)。 v6 stage 1 治理:status(active|pending|superseded|wrong,默认 active)、valid_until_ts(Unix 秒,0=永不过期)、 supersedes(旧记忆 id——记录新后自动把旧记忆标 superseded)。返回 {ok, id}。 注入由 config memory_inject 门控(默认关);召回检视见 recall_experiences;改状态见 set_experience_status。

set_experience_statusA

更新一条经验的治理状态(v6 stage 1,人工纠错)。

status ∈ {active, pending, superseded, wrong}。自由可逆(误标可改回): status→active 时自动 stamp last_reviewed。superseded_by(status=superseded 时指向替代者 id)。 valid_until_ts(Unix 秒,0=永不过期)。默认召回只含 active/pending 且未过期(superseded/wrong/expired 退出)。

mark_supersededB

把 old 记忆标 superseded(被 new 覆盖,退出召回)。set_experience_status 的便利封装。

recall_experiencesA

按关键词召回相关经验(只读,不调模型)。用于检视 Experience Memory 会召回什么。

默认 include_inactive=False 镜像生产 retrieve(只含 active/pending 且未过期); True=含 superseded/wrong/expired 供排查。返回 {count, experiences:[...完整 to_dict...]}。

review_documentA

审查一份文档(markdown/code/adr/rfc/config)。

多模型 fan-out(panel × dimensions)+ 知识库 retrieve(版本过滤)+ canonical 归一

  • 校准共识。返回结构化报告(consensus/majority/individual + calibrated_confidence)。

Args: content: 文档正文(markdown/adr/rfc/config)。 document_type: 文档类型,影响 prompt 模板。 files: 代码文件 {路径: 源码}(code 模式)。 adapter: "auto" 自动检测,或 "unity"/"generic"。 panel: 模型列表,None=默认面板(需配 OPENAI/ANTHROPIC/ARK key)。 dimensions: 审查维度,None=自动(core planner/safety + adapter 特定)。 retrieve_top_k: 知识库 retrieve 案例数。 extra_context: 额外补充 context(核心 context 由 adapter 自动聚合)。 output_format: json|markdown|sarif。json 返回结构化;其余额外加 rendered 字段。 timeout: 单模型超时秒。 effort: 思考强度 low/medium/high/xhigh/max;None=各模型默认。仅 Claude(output_config+thinking adaptive)/ OpenAI o 系列(reasoning_effort)生效,其余丢弃。Claude 默认 high 较贵,routine 方案可降 medium 省 token。 max_cost_usd: 单次 review 总成本上限(USD);None=无上限。设了则预 flight 估每 job 成本、按 panel 顺序裁剪直到估算超预算,report.budget.exhausted 标记是否裁过。

Returns: 报告 dict + cache_hit/reuse_count(+ rendered 若非 json)。

review_planC

审查实现方案/计划(design-question 模式)。等价 review_document(document_type="markdown")。

review_codeD

审查代码实现(code-review 模式)。等价 review_document(document_type="code")。

plan_taskB

把目标拆成可执行、可审查的计划。

Planner MVP 只返回结构化计划,不执行命令、不修改文件。它优先使用 planner_panel; 未配置时回退 consult_panel,再回退 review panel。首版按 panel 顺序尝试模型, 取第一个可解析计划作为结果,其余模型只作为失败回退,不做多模型 debate。

consult_problemA

外援会诊:当主模型卡住、没把握、连续调试失败或需要第三方视角时调用。

该工具只返回结构化建议,不执行命令、不修改文件。mode 可选 debugging/architecture/ performance/simplicity/game_design/challenge/planning。发送给外部模型前会做基础敏感信息 脱敏、输入长度上限控制和 consultant 白名单校验。panel None 时优先使用 consult_panel, 未配置则回退 review panel;consultants None 时使用 consult_consultants。

list_adaptersB

列出可用 ProjectAdapter + auto 检测结果。

list_reviewersC

列出可用 reviewer 角色(core 通用 + adapter 特定)。

list_consultantsA

列出可用外援会诊角色。

list_regionsA

List available Brain Regions.

list_allowed_rootsB

List workspace roots that BrainRegion file tools may read.

inspect_fileB

Inspect an allowed workspace file without returning contents.

read_textB

Read UTF-8 text from an allowed workspace file with line and byte limits.

search_textC

Search UTF-8 text files inside allowed workspace roots.

apply_text_patchC

Apply exact UTF-8 text replacements with a required sha256 guard.

workspace_run_checkC

Run an allowed test/lint check command inside an allowed workspace root.

list_skillsA

List registered Skill manifests(manifest-only, sanitized;status=experimental = 未接 production routing)。

Phase 4 discovery surface(Router API 调用点);不泄露 body ref,不触发 resolve。

route_regionsA

Recommend relevant Brain Regions from local deterministic rules.

This tool is read-only: it does not call models, read memory, or trigger review/consult/planner tools. File contents are ignored; file paths are used only as weak metadata.

suggest_workflowA

Suggest explicit manual next tool calls from Brain Region routing.

This tool is advisory only: it calls the local deterministic router, then returns candidate next actions such as plan_task, consult_problem, review_document, or review_code. It never calls those tools or models.

wake_gateB

Region-routing wake gate with false-negative defense (read-only sidecar).

Routes Brain Regions through retrieve -> escalate -> wake, adding sentinel (cross-domain risk keywords) and shadow (near-threshold) fallback wakes to defend against missed wakes. Returns an activation trace, wake_metrics vs optional gold_regions (metrics_status scored/unscored), and suggested actions. Never calls models or downstream tools.

inspectA

只读调试窗口(v5.x):把系统内部状态做成立即可见的可观测面。

view ∈ {all, activation, memory, run, calibration},只含请求的 section(all=全部 4)。

  • activation:重跑 wake_gate(无模型)看「该醒没醒」(给 gold_regions 才判漏唤醒)。

  • memory:Experience Memory 按 region 盘点 + 年龄。memory_manifest=True 附全量清单(Brain Diff 用;默认 False 精简)。

  • run:读历史 eval run 的已存 summary + per-task 5 态阶段时间线;无 run_id → 最近 N run 历史表。

  • calibration:judge 校准状态 + am-I-blocked。

纯只读:不调模型、不写、不重算(wake_gate 已验为 read-only sidecar)。

snapshotA

脑状态快照(可视化 Phase 1):投影 Inspector → 可序列化 BrainSnapshot 数据。

返回 snapshot.to_dict()(结构化数据,含 schema_version;可落盘后用 CLI --from 复渲染)。 HTML 渲染走 CLI brain-region snapshot(自包含静态面板)。恒取 memory/run/calibration; 仅当 problem 或 goal 非空才取 activation(无查询的空 wake 无意义)。纯只读:不调生成模型、不写。

list_knowledgeC

列出知识库案例索引(id/title/category/triggers)。

list_defaultsB

列出三层默认值及来源(builtin/config/env)。

list_model_routesA

Show how model specs resolve to official providers or configured endpoints.

This is a diagnostic tool only: it does not call models and never returns API key values. It helps distinguish bare model strings like claude-opus-4-8 from endpoint refs like modelbridge_anthropic/claude-opus-4-8.

suggest_panelA

Recommend a model panel from route/profile metadata without calling models.

Strategies include balanced, cheap_fast, best_reasoning, sleep, awake, and structured_output. The returned selected_panel can be copied into tools such as plan_task or consult_problem when the user chooses to spend tokens.

panel_statsB

缓存统计:审查总数 + 缓存命中省掉的重复审查数。

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/fanghaoling/brainregion'

If you have feedback or need assistance with the MCP directory API, please join our Discord server