MCP Context Provider
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ENVIRONMENT | No | Environment-specific context loading (e.g., prod, dev) | |
| AUTO_LOAD_CONTEXTS | No | Whether to automatically load context files at startup | true |
| CONTEXT_CONFIG_DIR | No | Directory path containing the context configuration files | ./contexts |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_tool_contextA | Get complete context (rules, syntax, preferences) for a specific tool |
| get_syntax_rulesC | Get syntax-specific rules for a tool category |
| list_available_contextsA | List all loaded context categories and their descriptions |
| apply_auto_correctionsC | Apply auto-correction patterns from matching contexts to text |
| build_injectionB | Build a complete injection payload (contexts + instincts) for a tool/input combination |
| list_instinctsB | List all loaded instincts with their confidence scores |
| store_instinctA | Store a new instinct candidate. Created as inactive with auto approval — use approve_instinct for human approval. |
| approve_instinctA | Approve an instinct for active use (sets approved_by to human) |
| reject_instinctA | Reject/deactivate an instinct and lower its confidence |
| record_outcomeB | Record a positive, negative, or neutral outcome for an instinct |
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 10 tools
Each tool targets a distinct aspect of context or instinct management, but 'list_available_contexts' and 'get_tool_context' both involve contexts, and 'apply_auto_corrections' and 'build_injection' both produce text modifications, creating minor potential for confusion.
All tool names use snake_case and follow a consistent verb_noun pattern (e.g., approve_instinct, list_instincts), making them predictable and easy to parse.
With 10 tools covering context retrieval, instinct lifecycle, and corrections, the set is well-scoped for its purpose without unnecessary redundancy.
Core workflows are covered, but there is no tool to update an instinct's details (e.g., change description) beyond recording outcomes and approval, leaving a minor gap.