Gravitas-Core-MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_last_stateA | Return the last known state (most recent snapshot + active task). Authoritative memory. |
| get_canonical_stateA | Return the last verified, immutable working state for rollback/recovery. |
| record_failureC | Record a failed strategy/command to prevent repetition. |
| resume_taskB | Load task and its context for resumption (model handover/restart). |
| controller_create_taskC | Create a new task and set state to PLANNING. |
| controller_transitionC | Transition task to a new state (PLANNING, CODING, EXECUTING, VERIFYING, FAILED_RETRY, ROLLBACK, COMPLETED). |
| controller_record_step_failureB | Record a step failure; may trigger FAILED_RETRY or ROLLBACK. |
| controller_get_stateC | Return current task state and policy info. |
| terminal_executeB | Execute a shell command with timeout and cwd. Returns stdout, stderr, exit_code. |
| terminal_start_backgroundC | Start a background process; use process_id to stop later. |
| terminal_stop_backgroundC | Terminate a background process by process_id. |
| terminal_list_backgroundA | List active background process ids. |
| browser_navigateC | Navigate to URL (Playwright). |
| browser_snapshotB | Capture DOM accessibility tree and console errors. |
| browser_screenshotB | Take screenshot; optional path to save file. |
| browser_get_console_errorsA | Return collected JS console errors since last navigate. |
| browser_hoverB | Hover over an element by CSS selector. |
| project_get_mapC | Recursive project structure with noise filtering. |
| memory_save_snapshotC | Save a context snapshot for current task (internal use). |
| memory_set_canonicalC | Set the canonical (immutable) state to a snapshot (after verification). |
| get_model_resume_packageB | Generate Model Resume Package for model swap/editor restart/crash recovery: goal, task, constraints, failures, safe/do-not-touch files. |
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 21 tools
Most tools have distinct purposes within their domains (browser, controller, terminal, state). However, `record_failure` and `controller_record_step_failure` overlap in concept, potentially causing confusion. The state retrieval tools (`get_canonical_state`, `get_last_state`, `get_model_resume_package`) are distinct but require careful reading of descriptions.
Naming is consistent within domains: browser_*, controller_*, terminal_*. However, across domains, there is inconsistency: some tools use verb_noun order (e.g., `browser_get_console_errors`) while others use noun_verb (e.g., `get_canonical_state`). The pattern is mostly predictable but not uniform.
21 tools is on the higher side but still reasonable for the server's scope, which includes browser automation, task management, terminal execution, and state persistence. Each tool has a clear role, and no tool feels redundant or out of place.
The tool set covers the core workflows: browser interaction, task lifecycle, terminal commands, and state recovery. Minor gaps exist (e.g., no file read/edit tool), but the server is focused on orchestration rather than full development, so these omissions are acceptable.