io.github.soluai-spa由 GitHub 账号 soluai-spa 发布v1.1.2更新于 Oct 24, 2026
Living technical memory for AI agents: recall approved project context, record what was learned.
SoluCortex MCP 为助手提供项目的“活技术记忆”：检索已批准的决策、约定与风险，并记录任务中学到的内容。
Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。
把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。
阅读 https://sourceweft.com/mcp/io.github.soluai-spa%2Fsolucortex-mcp/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。把它添加到你客户端的 mcpServers 配置中。
{
"mcpServers": {
"solucortex": {
"type": "http",
"url": "https://mcp.solucortex.ai/mcp",
"headers": {
"Authorization": "Bearer <YOUR_TOKEN>"
}
}
}
}[PyPI] [CI] [Python] [License: MIT]
Official Model Context Protocol server for SoluCortex — living technical memory for AI agents.
Connect any MCP-compatible agent (Claude Code, Claude Desktop, Cursor, Codex, Cline, …) to your SoluCortex project so it can recall the decisions, conventions, risks and architecture that matter before it works, and remember what it learns when it's done.
Website: solucortex.ai ·
Setup guide: solucortex.ai/docs/mcp ·
Tools reference: solucortex.ai/docs/mcp-tools ·
PyPI: solucortex-mcp ·
MCP Registry: io.github.soluai-spa/solucortex-mcp
[SoluCortex MCP demo: recall approved context at task start, remember learnings at close]
Governance by design: agents propose, humans govern. Agents can never change a memory's
status, rewrite its metadata, or delete it — edits go back to pending and deletions only happen from the SoluCortex panel.
scx_) — get it from your
SoluCortex dashboard.uv (recommended), Python ≥ 3.10, or Docker.The server is configured entirely through environment variables:
Run with MCP_TRANSPORT=http (or --http) to serve Streamable HTTP on $PORT
(default 8080) — the mode behind https://mcp.solucortex.ai. Credentials travel with
each request and the environment is ignored:
GET /health (and /healthz locally; Cloud Run's frontend intercepts /healthz) responds without auth. The MCP endpoint is
/mcp, runs stateless, and shares nothing between requests/tenants.
Never commit your API key. Keep it in your MCP client config's env block or a local .env
(see .env.example).
The hosted server at https://mcp.solucortex.ai/mcp speaks Streamable HTTP; your key
travels with each request:
Or in any client with remote MCP support:
Add to the client's MCP config (claude_desktop_config.json, Cursor mcp.json, etc.):
Prebuilt image on GHCR:
Or build it yourself:
The server speaks MCP over stdio, so clients launch it as a subprocess (-i keeps stdin open).
Once connected, give your agent the methodology too: copy
templates/AGENTS.md into the root of your repo (it works as
AGENTS.md or CLAUDE.md). The MCP handshake already carries these instructions — the
file lets you version them alongside your code, extend them with your own conventions,
and optionally enable the commented Claude Code hook recipe for guaranteed recall.
type vocabulary: the canonical set is architecture, decision, risk, convention, bug_history, tech_debt, sensitive_module, learning, external_integration. Some backends
accept an older set (technical_decision, historical_bug, current_state, task_closure).
The server passes type through and surfaces HTTP 422 so you can retry with the other set.MIT — see LICENSE.
来源：README.md，提交 b97a3af
SoluCortex: recall task context
Build living context for a task (POST /context/build). Call this at the START of a task, before touching code: returns approved, active memories (decisions, conventions, risks, sensitive modules, architecture) ranked by semantic similarity + importance. Uses OpenAI embeddings (slower, 20 req/min).
query必填project_idSoluCortex: semantic memory search
Ad-hoc semantic search of memories (POST /search/semantic). Use for specific questions during a task (e.g. 'how is authentication implemented?'), distinct from recall which builds the full startup context. Uses OpenAI embeddings (20 req/min).
limitquery必填project_idSoluCortex: record a memory
Record a memory in SoluCortex (POST /memories). Call when closing a task or making a relevant technical decision. As an authorized agent (Bearer api_key), the memory is stored with status 'approved' and traced. Never store real secrets: if you find one, record location/type/severity and action taken, with a redacted reference.
type必填title必填content必填importanceproject_idSoluCortex: update a memory (requires human re-approval)
Correct an existing memory (PATCH /memories/{id}). Agents propose, humans govern: the edit is applied but the memory returns to PENDING until a human re-approves it. ALWAYS tell the user the change awaits their approval in the SoluCortex panel. Status changes are not possible here.
typetitlecontentmemory_id必填importanceSoluCortex: flag a memory for human review
Flag a memory as outdated/incorrect (POST /memories/{id}/flag). The memory is marked for human review in the SoluCortex panel; nothing is deleted or unpublished. ALWAYS tell the user a memory awaits their decision in the panel. Deletion is human-only by design.
reason必填memory_id必填suggested_actionSoluCortex: list memories
List the project's memories without semantic search (GET /memories). Useful for quick inspection/audit or to confirm a just-created memory was stored. Does not consume OpenAI quota.
limitproject_id已满足适用检查项的 100%
该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。
claude mcp add --transport http solucortex https://mcp.solucortex.ai/mcp \ --header "Authorization: Bearer scx_xxx" \ --header "X-Solucortex-Project: your-project-uuid"{ "mcpServers": { "solucortex": { "type": "http", "url": "https://mcp.solucortex.ai/mcp", "headers": { "Authorization": "Bearer scx_xxx", "X-Solucortex-Project": "your-project-uuid" } } }}claude mcp add solucortex \ -e SOLUCORTEX_API_KEY=scx_xxx \ -e SOLUCORTEX_PROJECT_ID=your-project-uuid \ -- uvx solucortex-mcp{ "mcpServers": { "solucortex": { "command": "uvx", "args": ["solucortex-mcp"], "env": { "SOLUCORTEX_API_KEY": "scx_xxx", "SOLUCORTEX_PROJECT_ID": "your-project-uuid" } } }}git clone https://github.com/soluai-spa/solucortex-mcpcd solucortex-mcpcp .env.example .env # fill in your key./run.sh # loads .env, then runs via uv# or, with SOLUCORTEX_* already exported: uv run solucortex-mcpdocker run --rm -i \ -e SOLUCORTEX_API_KEY=scx_xxx \ ghcr.io/soluai-spa/solucortex-mcp:latestdocker build -t solucortex-mcp .docker run --rm -i \ -e SOLUCORTEX_API_KEY=scx_xxx \ -e SOLUCORTEX_PROJECT_ID=your-project-uuid \ solucortex-mcpuv syncuv run solucortex-mcp # run (stdio)MCP_TRANSPORT=http uv run solucortex-mcp # run (HTTP on :8080)uv run pytest # test suitenpx @modelcontextprotocol/inspector uv run solucortex-mcp # interactive test