io.github.soluai-spaPublished by GitHub account soluai-spav1.1.2Updated Oct 24, 2026
Living technical memory for AI agents: recall approved project context, record what was learned.
SoluCortex MCP gives an assistant a project's living technical memory: recall approved decisions, conventions and risks, and record what it learns.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.soluai-spa%2Fsolucortex-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Add this to your client's mcpServers config.
{
"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.
Source: README.md at commit 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).
queryrequiredproject_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).
limitqueryrequiredproject_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.
typerequiredtitlerequiredcontentrequiredimportanceproject_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_idrequiredimportanceSoluCortex: 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.
reasonrequiredmemory_idrequiredsuggested_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_id100% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
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