SoluCortex
Server Details
Give your AI agent persistent, governed memory for every project. At task start it recalls the approved decisions, conventions, risks and architecture (semantic search, ranked by importance); at close it proposes what was learned as typed memories that you review and approve — governance, not a notes dump. Agents propose, humans govern: edits go back to pending and deletion is human-only by design. Connect Claude Code, Cursor, Claude Desktop or any MCP client in two minutes with just your API key — hosted (nothing to install) or locally via uvx solucortex-mcp. Built by SoluAI and dogfooded daily: SoluCortex is developed using its own living memory.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- soluai-spa/solucortex-mcp
- GitHub Stars
- 0
- Server Listing
- solucortex-mcp
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 6 tools
Each tool has a distinct intended action: record, list, search, build context, update, or flag. The only potential overlap is between recall and search, but the descriptions clearly separate start-of-task context building from ad-hoc semantic queries.
All tools share the solucortex_ prefix and snake_case style, but the pattern is mixed: flag_memory, list_memories, and update_memory follow verb_noun, while recall, remember, and search are bare verbs. This makes the set readable but not fully predictable.
Six tools is well-scoped for a project memory system. Each tool covers a meaningful operation without redundancy or bloat, making the surface easy for an agent to navigate.
The toolset covers the full memory lifecycle: create, list, semantic search, context building, update, and flag for review. Deletion is intentionally human-only, which is clearly documented and not a functional gap for the agent.
Available Tools
6 toolssolucortex_flag_memoryAIdempotentInspect
Flag a memory as outdated/incorrect (POST /memories/{id}/flag).
The memory is marked for human review in the SoluCortex panel; nothing is deleted or unpublished.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.
Inputs: reason (required), memory_id (required), suggested_action. Returns: object
solucortex_list_memoriesARead-onlyInspect
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.
Inputs: limit, project_id. Returns: object
solucortex_recallARead-onlyInspect
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).Inputs: query (required), project_id. Returns: object
solucortex_rememberAInspect
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.Inputs: type (required), title (required), content (required), importance, +1 more. Returns: object
solucortex_searchARead-onlyInspect
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).
Inputs: query (required), limit, project_id. Returns: object
solucortex_update_memoryAInspect
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.Inputs: memory_id (required), type, title, content, +1 more. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
A second brain for your AI agent. Shared memory for your team's AI agents, plus public and private knowledge bases — works with ChatGPT, Claude, Cursor and any MCP client.
Hosted memory for your AI coding agents. Projects, decisions, to-dos and lessons that carry across Claude, Cursor and ChatGPT. Nothing to install: sign in at flowstatemcp.com and connect. Encrypted at rest, backed up, export or erase any time. Beta: 6 months free, then half price.
Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.
Team memory for AI coding agents and code reviews, reviewed by humans and served over MCP.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenancePersistent project memory and task management for AI coding agents through MCP. Lets Claude Code, Cursor, Codex and other MCP clients save decisions and bug fixes, search relevant context, and reuse it across sessions.1MIT
- AlicenseBqualityBmaintenancePersistent, local memory for AI coding agents that learns how you work, not just what you said. Supports Claude Code, Codex CLI, Cursor, and any MCP client.7998 PyPI77MIT
- AlicenseAqualityCmaintenanceShared, versioned memory for your agents across Claude Code, Cursor, Kiro and Grok. One MCP server, sourced answers, full history.3MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI coding agents to maintain persistent, cross-session memory of codebase architecture, naming conventions, and decisions through MCP tools. Eliminates repetitive project re-explanation by automatically injecting stored context into every session with local-first SQLite storage and optional team sharing capabilities.4MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.