Skip to content

io.github.soluai-spa/solucortex-mcp

by soluai-spa · remote · local (pypi) · no sign-in to list tools · v1.1.2 · published by GitHub user soluai-spa

Living technical memory for AI agents: recall approved project context, record what was learned.

Changes · 41 high finding
CompareRegistry entry

6 tools: 4 change things and 2 only read.

Scanned Oct 21, 2026

2 checks matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http solucortex https://mcp.solucortex.ai/mcp --header 'Authorization: <your-authorization>'

Findings

Matches of fixed checks, with the text they matched.

1 high1 info
  • Highsolucortex_remember

    The input schema at properties.content.description refers to ".env".

    Matched text

    inputSchema.properties.content.description: "...nclude real secrets (tokens, passwords, .env, credentials)."

    What this check looks for
  • Infosolucortex_remember

    The input schema at properties.content.description mentions "credentials".

    Matched text

    inputSchema.properties.content.description: "...real secrets (tokens, passwords, .env, credentials)."

    What this check looks for

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

6 tools

Changes things 4Claude Code: ask
  • solucortex_flag_memoryFlag a memory as outdated/incorrect (POST /memories/{id}/flag).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Flag a memory as outdated/incorrect (POST /memories/{id}/flag). The memory is marked for human review in the SoluCortex panel; nothing is deleted or unpublished.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.

    Annotations the server declares

    • title: SoluCortex: flag a memory for human review
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • solucortex_recallBuild living context for a task (POST /context/build).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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).

    Annotations the server declares

    • title: SoluCortex: recall task context
    • readOnlyHint: true
    • openWorldHint: true
  • solucortex_rememberRecord a memory in SoluCortex (POST /memories).2 findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    Findings

    • High

      The input schema at properties.content.description refers to ".env".

      Matched text

      inputSchema.properties.content.description: "...nclude real secrets (tokens, passwords, .env, credentials)."

      What this check looks for
    • Info

      The input schema at properties.content.description mentions "credentials".

      Matched text

      inputSchema.properties.content.description: "...real secrets (tokens, passwords, .env, credentials)."

      What this check looks for
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: SoluCortex: record a memory
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • solucortex_update_memoryCorrect an existing memory (PATCH /memories/{id}).No findings

    Why it is in this group

    • The name "solucortex_update_memory" says "update": a word for a change.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: SoluCortex: update a memory (requires human re-approval)
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Only reads 2Claude Code: allow
  • solucortex_list_memoriesList the project's memories without semantic search (GET /memories).No findings

    Why it is in this group

    • The name "solucortex_list_memories" says "list": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: SoluCortex: list memories
    • readOnlyHint: true
    • openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.1.2. Values in angle brackets are yours to fill in.

claude mcp add --transport http solucortex https://mcp.solucortex.ai/mcp --header 'Authorization: <your-authorization>'

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__solucortex__solucortex_search",
      "mcp__solucortex__solucortex_list_memories"
    ],
    "ask": [
      "mcp__solucortex__solucortex_recall",
      "mcp__solucortex__solucortex_remember",
      "mcp__solucortex__solucortex_update_memory",
      "mcp__solucortex__solucortex_flag_memory"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as solucortex. Review it before you use it.