solucortex-mcp
Living technical memory for AI agents: recall approved project context, record what was learned.
Sollte ich dies verwenden
Qualität und Sicherheit
Basierend auf einer automatisierten Analyse der Tool-Definitionen und der Einhaltung des Protokolls.
Kontextkosten
Dies ist die ungefähre Anzahl der Tokens, die jedes Mal verbraucht werden, wenn die Tools des Servers in den Kontext eines Modells geladen werden. Höhere Werte verringern die Aufmerksamkeit, die für andere Aufgaben verfügbar ist.
Installieren
Installation mit einem Klick
Fügen Sie dies Ihrer Datei `claude_desktop_config.json` hinzu:
{
"mcpServers": {
"solucortex-mcp": {
"command": "uvx",
"args": [
"solucortex-mcp"
]
}
}
}Ausführbare Pakete
1.1.2stdioRemote-Endpunkte
https://mcp.solucortex.ai/mcpstreamable-httpWas es kann
Tool-Inventar
Tools (6)
🟢solucortex_recall(query, project_id)
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).
Eingabe-Schema
{
"type": "object",
"properties": {
"query": {
"description": "Describe the current task/module in natural language, e.g. 'implement API key rotation in the secrets module'. Used to semantically retrieve the most relevant memories.",
"title": "Query",
"type": "string"
},
"project_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Project UUID. If omitted, the session default applies, else the backend infers it from the API key.",
"title": "Project Id"
}
},
"required": [
"query"
],
"title": "solucortex_recallArguments"
}Ausgabe-Schema
{
"type": "object",
"additionalProperties": true,
"title": "solucortex_recallDictOutput"
}🟢solucortex_search(query, limit, project_id)
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).
Eingabe-Schema
{
"type": "object",
"properties": {
"query": {
"description": "Question or topic to search across the project's memories.",
"title": "Query",
"type": "string"
},
"limit": {
"default": 10,
"description": "Max memories to return.",
"maximum": 50,
"minimum": 1,
"title": "Limit",
"type": "integer"
},
"project_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Project UUID. If omitted, the session default applies, else the backend infers it from the API key.",
"title": "Project Id"
}
},
"required": [
"query"
],
"title": "solucortex_searchArguments"
}Ausgabe-Schema
{
"type": "object",
"additionalProperties": true,
"title": "solucortex_searchDictOutput"
}🟢solucortex_remember(type, title, content, importance, project_id)
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.
Eingabe-Schema
{
"type": "object",
"properties": {
"type": {
"description": "Memory type. The backend validates the value. Canonical vocabulary: architecture, decision, risk, convention, bug_history, tech_debt, sensitive_module, learning, external_integration. (Older backends may use technical_decision, historical_bug, current_state, task_closure.) On HTTP 422, retry with the alternate vocabulary.",
"title": "Type",
"type": "string"
},
"title": {
"description": "Short, clear title (~80 chars max).",
"maxLength": 120,
"title": "Title",
"type": "string"
},
"content": {
"description": "Full content: what to remember, why it matters, where it applies and what it prevents. NEVER include real secrets (tokens, passwords, .env, credentials).",
"title": "Content",
"type": "string"
},
"importance": {
"default": 5,
"description": "Priority 1-10. Default 5. 6-7 high; 8-9 important decision/risk/convention; 10 critical.",
"maximum": 10,
"minimum": 1,
"title": "Importance",
"type": "integer"
},
"project_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Project UUID. If omitted, the session default applies, else the backend infers it from the API key.",
"title": "Project Id"
}
},
"required": [
"type",
"title",
"content"
],
"title": "solucortex_rememberArguments"
}Ausgabe-Schema
{
"type": "object",
"additionalProperties": true,
"title": "solucortex_rememberDictOutput"
}🟡solucortex_update_memory(memory_id, content, title, importance, type)
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.
Eingabe-Schema
{
"type": "object",
"properties": {
"memory_id": {
"description": "UUID of the memory to correct.",
"title": "Memory Id",
"type": "string"
},
"content": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Corrected full content.",
"title": "Content"
},
"title": {
"anyOf": [
{
"maxLength": 120,
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Corrected title.",
"title": "Title"
},
"importance": {
"anyOf": [
{
"maximum": 10,
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"description": "Corrected priority 1-10.",
"title": "Importance"
},
"type": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Corrected memory type (one of the 9 canonical types).",
"title": "Type"
}
},
"required": [
"memory_id"
],
"title": "solucortex_update_memoryArguments"
}Ausgabe-Schema
{
"type": "object",
"additionalProperties": true,
"title": "solucortex_update_memoryDictOutput"
}⚪solucortex_flag_memory(memory_id, reason, suggested_action)
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.
Eingabe-Schema
{
"type": "object",
"properties": {
"memory_id": {
"description": "UUID of the memory to flag.",
"title": "Memory Id",
"type": "string"
},
"reason": {
"description": "Why it needs review: outdated, incorrect, duplicated... (10-500 chars).",
"maxLength": 500,
"minLength": 10,
"title": "Reason",
"type": "string"
},
"suggested_action": {
"default": "review",
"description": "What you suggest the human does: update, archive, delete or review.",
"title": "Suggested Action",
"type": "string"
}
},
"required": [
"memory_id",
"reason"
],
"title": "solucortex_flag_memoryArguments"
}Ausgabe-Schema
{
"type": "object",
"additionalProperties": true,
"title": "solucortex_flag_memoryDictOutput"
}🟢solucortex_list_memories(limit, project_id)
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.
Eingabe-Schema
{
"type": "object",
"properties": {
"limit": {
"default": 20,
"description": "Max memories to return.",
"maximum": 100,
"minimum": 1,
"title": "Limit",
"type": "integer"
},
"project_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Project UUID. If omitted, the session default applies, else the backend infers it from the API key.",
"title": "Project Id"
}
},
"title": "solucortex_list_memoriesArguments"
}Ausgabe-Schema
{
"type": "object",
"additionalProperties": true,
"title": "solucortex_list_memoriesDictOutput"
}Community
Nachweis