usecortex-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| API_KEY | Yes | The API key generated from the UseCortex dashboard (Settings → API Keys). This is used in the Authorization header as a Bearer token. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| query_knowledgeB | Search your knowledge base using AI. Ask a natural language question and get an answer based on your stored knowledge. |
| list_topicsB | List all knowledge topics in your base. |
| add_knowledgeC | Write new knowledge to your base. Store facts, decisions, patterns, or any information your AI should remember. |
| get_topicC | Retrieve all knowledge entries for a specific topic. |
| search_knowledgeA | Search knowledge entries by keyword (text match). Use query_knowledge for AI-powered answers. |
| capture_sessionA | Capture an AI session summary into persistent memory. Store what you learned, decided, or built during this session. Requires Memory plan. |
| recall_memoryB | Search across all captured session memories using AI. Ask what you worked on, what decisions were made, or what patterns were found. Requires Memory plan. |
| list_sessionsB | List recent captured session memories. Requires Memory plan. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Most tools have distinct purposes, but there is some overlap between query_knowledge and search_knowledge, as both involve searching knowledge, though their descriptions clarify different methods (AI-powered vs. keyword). The other tools target clearly different operations like adding, retrieving, listing, and capturing.
All tool names follow a consistent verb_noun pattern with snake_case, such as add_knowledge, capture_session, get_topic, list_sessions, list_topics, query_knowledge, recall_memory, and search_knowledge. This uniformity makes the set predictable and easy to understand.
With 8 tools, this server is well-scoped for managing knowledge and memory, covering core operations like adding, retrieving, listing, and searching. The count is appropriate, providing comprehensive functionality without being overwhelming or insufficient.
The tool set covers key CRUD-like operations for knowledge and session memory, including add, get, list, and search. A minor gap is the lack of update or delete tools for knowledge or sessions, which might limit full lifecycle management, but agents can likely work around this.