cognitive-harness-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| COGNITIVE_MEMORY_PATH | No | 记忆 JSON 文件路径 (Memory JSON file path) | ~/.local/share/TeleAgent/memory/cognitive-memory.json |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| cognitive_searchA | 按关键词、内容类型、生活域等条件检索用户认知记忆,返回与查询最相关的记忆条目(按置信度降序,支持分页)。 当对话涉及用户的历史偏好、身份背景、正在进行的项目、过往事件时,先调用此工具获取上下文再作答,避免凭猜测回复。 Args:
Returns(结构化): { "total": number, // 总命中数 "count": number, // 本次返回数 "offset": number, "has_more": boolean, // 是否还有更多 "entries": [{ id, type, content, domain, depth, confidence, rule_status, scope, timestamp, is_dynamic, pending_follow_up }] } Examples:
Error:
|
| cognitive_writeA | 写入一条关于用户的认知记忆。适用于对话中出现的:客观事实、明确的偏好或规则、表达的真实含义、情绪模式、价值观、工作流程、重要事件。 规则类记忆(protocol/pragmatic)必须带因果说明:记录"为什么"而不是扁平结论。例如不要只记"用户发长段落时不要直接执行",而要记"用户长文+探讨意图=头脑风暴的邀请,直接动手会打断思路"。 Args:
Returns: { "memory_id": string, // 新记忆 ID "type": string, "content": ..., "domain": string, "confidence": number } |
| cognitive_updateA | 更新一条已存在的记忆的部分字段。找不到该记忆时返回错误。 Args:
Returns: { "success": boolean, "memory": { 更新后的完整条目 } 或 null } |
| cognitive_forgetA | 删除或降级一条用户记忆。默认 degrade(版本化降级):保留证据链、置信度减半,适用于"用户想法变了"的场景;delete 为彻底删除,不可恢复,请谨慎使用。 Args: memory_id: 要遗忘的记忆 ID mode: 'degrade'(默认,版本化降级)| 'delete'(彻底删除) reason: 遗忘原因,可选 Returns: { "success": boolean, "mode": string } |
| cognitive_summaryA | 获取压缩的用户认知画像("印象"):交互偏好、核心画像、分域认知、已知事实、待跟进。适用于对话开始、或需要全面理解用户时。比逐条检索更高效。 Args: format: 'system_prompt'(默认,返回带引导语的注入片段)| 'markdown'(纯摘要) Returns: { "summary": string, "memory_count": number } |
| cognitive_statsA | 返回记忆存储的统计信息:总量、按类型分布、按领域分布、确认规则数。用于了解记忆覆盖面。 |
| cognitive_listB | 按时间倒序列出全部用户记忆(分页)。用于浏览记忆全貌。默认返回最近 20 条。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool targets a distinct operation: search, list, stats, summary, write, update, and forget are clearly separated by purpose. Search and list both retrieve memories but are differentiated by query-based filtering versus chronological browsing.
All tools share the cognitive_ prefix and mostly use verb-style names like cognitive_search, cognitive_write, and cognitive_update. The pattern is slightly weakened by noun-style names cognitive_stats and cognitive_summary, but the convention remains highly predictable.
Seven tools is well-scoped for a memory management server: full CRUD plus search, statistics, and aggregated summary. Each tool earns its place without redundancy or bloat.
The tool surface fully covers the memory lifecycle: write, read via search/list/summary, update, and forget with both degrade and delete modes. The addition of stats and summary fills retrieval and introspection needs, leaving no obvious gaps.