srdcheck
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| jurisdiction | Look up whether a named entity exists in the loaded rulesets' content registries. exit_code 0 = known content (categories in payload); 2 = unknown or third-party content, honestly refused. |
| attack_modifiersA | Compose an attack roll's Advantage/Disadvantage from both combatants' conditions and distance (Prone's 5-foot flip, Blinded, Restrained, Paralyzed, Stunned, Invisible with the seen exception, the Grappled attacker rule). Exhaustion is returned as a flat modifier, never Advantage. Genuinely ambiguous rules text (e.g. a seen Invisible target) returns cannot-adjudicate with the ambiguous sentence cited. |
| event_applyA | The reducer (fold): apply one declared event to a state object and receive the verdict plus the stamped next_state (lineage: predecessor hash, causing event, rule ids, rule-vs-ruling kind). Event types: turn-start (budgets reset, Reaction returns), round-advance, action / bonus-action / reaction / free-interaction / move / stand-up (validated against budgets and conditions; may carry spell:{level} and concentration_on), condition-gained, condition-ended, ruling (GM discretion — recorded and tagged as discretion, never as a rule). srdcheck never produces an event, never advances time on its own, never generates randomness: the caller owns the loop; this is the fold. |
| mage_hand_useA | Adjudicate one proposed use of the Mage Hand cantrip: granted uses (manipulate, open unlocked, stow/retrieve, pour), prohibitions (attack, activate magic items), the 10-pound carry limit and 30-foot range leash. Uses outside the text's can/can't lists return cannot-adjudicate — the GM's call, honestly labeled. |
| reaction_availableA | Is taking a Reaction legal right now? Reactions refresh at the start of your own turn (not the round) and are usable on your own turn. |
| roll_composeA | Compose net Advantage/Disadvantage from lists of sources: multiple sources never add dice, and any Advantage plus any Disadvantage yields a straight single-d20 roll regardless of counts. Optionally notes the reroll-one-die-only rule. |
| turn_optionsB | Enumerate what remains legal this turn given the same state shape as turn.plan (no plan). Options carry feet_remaining, stand-up cost, crawl mode, and spell-slot availability. Consistency-tested against turn.plan: everything enumerated is accepted, everything past a boundary rejected. |
| turn_planA | Judge a whole proposed turn under SRD 5.2.1 ACTION ECONOMY: action/bonus-action/reaction/free-interaction budgets, movement (crawling, standing from Prone, Grappled speed 0), Incapacitated, and the one-spell-slot-per-turn rule. Returns legal/illegal/cannot-adjudicate with citations; illegal verdicts name the first offending step. Scope: this checks the turn's economy only — it does NOT verify that a feature grants a given action (e.g. two-weapon fighting or Extra Attack prerequisites). Unmodeled conditions and out-of-range inputs (negative speed, spell level >9) return exit 2 rather than a guess. |
| ttt_moveA | Judge one proposed tic-tac-toe move. Board is a 9-character string of X, O, and . (dot = empty), cells 1-9 left-to-right top-to-bottom. Checks turn order, cell validity, occupancy, and whether the game has already ended. |
| ttt_optionsA | Enumerate the legal moves for a player on a board (same encoding as ttt.move). Empty when it is not the player's turn or the game has ended. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/chaoz23/srdcheck'
If you have feedback or need assistance with the MCP directory API, please join our Discord server