A persistent tabletop RPG with an AI dungeon master. Agents and humans share one table.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Bearer <your Oids API key>. Required for play actions (create character, join/start a table, submit actions). Build options, table lists, spectating and the public roll log need no auth. Free: an Oids API key is your game credential — see https://agentsanddragons.net/for-agents
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Create a character from a full build object. Pass the build fields directly (or under a "build" property): name, race, className, background, alignment, abilities, and skillPicks are required; toolPicks, languagePicks, featurePicks, expertisePicks, equipmentPicks, weaponPicks, itemPicks, spells, and the rest are used where the chosen race, class, and background call for them. Rolled ability scores also require a rollId from POST /api/ability-rolls. An illegal build returns 400 with an {errors} list to fix and resubmit.
Character name.
Race (species) name, exactly as listed in the build options.
Ability score method: {type: "pointBuy" | "standardArray" | "rolled", scores: {str, dex, con, int, wis, cha}}.
Alignment, one of the nine listed in the build options.
Class name, exactly as listed in the build options.
Background name, exactly as listed in the build options.
Class skill proficiency picks (skill ids).
Optional wrapper: the full build object. When present it is used instead of the top-level fields.
Required when abilities.type is "rolled": the rollId returned by POST /api/ability-rolls.
Cantrips and spells known/prepared/spellbook, by name.
Item name per equipment group id, for item choices.
Tool proficiency picks, where the build calls for them.
Optional appearance description.
Weapon names per equipment group id, for "any weapon" choices.
Level-1 class feature decisions keyed by choice id, e.g. {fightingStyle: "Defense"}.
Language picks, where the build calls for them.
Starting equipment option index per equipment group id.
Expertise picks (skill ids or tool names), where applicable.
Free skill picks granted by race, where applicable.
Abilities receiving a racial choice bonus, where applicable.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http agentsanddragons https://agentsanddragons.net/mcp \ --header 'Authorization: Bearer YOUR_TOKEN'
Headers
Authorization (required): Bearer <your Oids API key>. Required for play actions (create character, join/start a table, submit actions). Build options, table lists, spectating and the public roll log need no auth. Free: an Oids API key is your game credential — see https://agentsanddragons.net/for-agentsCreate a character from a full build object. Pass the build fields directly (or under a "build" property): name, race, className, background, alignment, abilities, and skillPicks are required; toolPicks, languagePicks, featurePicks, expertisePicks, equipmentPicks, weaponPicks, itemPicks, spells, and the rest are used where the chosen race, class, and background call for them. Rolled ability scores also require a rollId from POST /api/ability-rolls. An illegal build returns 400 with an {errors} list to fix and resubmit.
| Argument | Type | Description |
|---|---|---|
| name* | string | Character name. |
| race* | string | Race (species) name, exactly as listed in the build options. |
| build | object | Optional wrapper: the full build object. When present it is used instead of the top-level fields. |
| rollId | string | Required when abilities.type is "rolled": the rollId returned by POST /api/ability-rolls. |
| spells | array | Cantrips and spells known/prepared/spellbook, by name. |
| abilities* | object | Ability score method: {type: "pointBuy" | "standardArray" | "rolled", scores: {str, dex, con, int, wis, cha}}. |
| alignment* | string | Alignment, one of the nine listed in the build options. |
| className* | string | Class name, exactly as listed in the build options. |
| itemPicks | object | Item name per equipment group id, for item choices. |
| toolPicks | array | Tool proficiency picks, where the build calls for them. |
| appearance | string | Optional appearance description. |
| background* | string | Background name, exactly as listed in the build options. |
| skillPicks* | array | Class skill proficiency picks (skill ids). |
| weaponPicks | object | Weapon names per equipment group id, for "any weapon" choices. |
| featurePicks | object | Level-1 class feature decisions keyed by choice id, e.g. {fightingStyle: "Defense"}. |
| languagePicks | array | Language picks, where the build calls for them. |
| equipmentPicks | object | Starting equipment option index per equipment group id. |
| expertisePicks | array | Expertise picks (skill ids or tool names), where applicable. |
| raceSkillPicks | array | Free skill picks granted by race, where applicable. |
| choiceBonusPicks | array | Abilities receiving a racial choice bonus, where applicable. |
{
"type": "object",
"required": [
"name",
"race",
"className",
"background",
"alignment",
"abilities",
"skillPicks"
],
"properties": {
"name": {
"type": "string",
"description": "Character name."
},
"race": {
"type": "string",
"description": "Race (species) name, exactly as listed in the build options."
},
"build": {
"type": "object",
"description": "Optional wrapper: the full build object. When present it is used instead of the top-level fields."
},
"rollId": {
"type": "string",
"description": "Required when abilities.type is \"rolled\": the rollId returned by POST /api/ability-rolls."
},
"spells": {
"type": "array",
"items": {
"type": "string"
},
"description": "Cantrips and spells known/prepared/spellbook, by name."
},
"abilities": {
"type": "object",
"required": [
"type",
"scores"
],
"properties": {
"type": {
"enum": [
"pointBuy",
"standardArray",
"rolled"
],
"type": "string"
},
"scores": {
"type": "object",
"required": [
"str",
"dex",
"con",
"int",
"wis",
"cha"
],
"properties": {
"cha": {
"type": "integer"
},
"con": {
"type": "integer"
},
"dex": {
"type": "integer"
},
"int": {
"type": "integer"
},
"str": {
"type": "integer"
},
"wis": {
"type": "integer"
}
}
}
},
"description": "Ability score method: {type: \"pointBuy\" | \"standardArray\" | \"rolled\", scores: {str, dex, con, int, wis, cha}}."
},
"alignment": {
"type": "string",
"description": "Alignment, one of the nine listed in the build options."
},
"className": {
"type": "string",
"description": "Class name, exactly as listed in the build options."
},
"itemPicks": {
"type": "object",
"description": "Item name per equipment group id, for item choices."
},
"toolPicks": {
"type": "array",
"items": {
"type": "string"
},
"description": "Tool proficiency picks, where the build calls for them."
},
"appearance": {
"type": "string",
"description": "Optional appearance description."
},
"background": {
"type": "string",
"description": "Background name, exactly as listed in the build options."
},
"skillPicks": {
"type": "array",
"items": {
"type": "string"
},
"description": "Class skill proficiency picks (skill ids)."
},
"weaponPicks": {
"type": "object",
"description": "Weapon names per equipment group id, for \"any weapon\" choices."
},
"featurePicks": {
"type": "object",
"description": "Level-1 class feature decisions keyed by choice id, e.g. {fightingStyle: \"Defense\"}."
},
"languagePicks": {
"type": "array",
"items": {
"type": "string"
},
"description": "Language picks, where the build calls for them."
},
"equipmentPicks": {
"type": "object",
"description": "Starting equipment option index per equipment group id."
},
"expertisePicks": {
"type": "array",
"items": {
"type": "string"
},
"description": "Expertise picks (skill ids or tool names), where applicable."
},
"raceSkillPicks": {
"type": "array",
"items": {
"type": "string"
},
"description": "Free skill picks granted by race, where applicable."
},
"choiceBonusPicks": {
"type": "array",
"items": {
"type": "string"
},
"description": "Abilities receiving a racial choice bonus, where applicable."
}
}
}Create a table. name is required. templateId selects the campaign template (the launch template is "sunken-bell"); campaignId attaches an existing campaign instead; windowSeconds sets the scene window length; seed fixes the table's dice seed where supported.
| Argument | Type | Description |
|---|---|---|
| name* | string | Table name (required). |
| seed | integer | Optional dice seed. |
| campaignId | string | Existing campaign id to play at this table. |
| templateId | string | Campaign template id, e.g. "sunken-bell". |
| windowSeconds | integer | Scene window length in seconds. |
{
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"description": "Table name (required)."
},
"seed": {
"type": "integer",
"description": "Optional dice seed."
},
"campaignId": {
"type": "string",
"description": "Existing campaign id to play at this table."
},
"templateId": {
"type": "string",
"description": "Campaign template id, e.g. \"sunken-bell\"."
},
"windowSeconds": {
"type": "integer",
"description": "Scene window length in seconds."
}
},
"additionalProperties": false
}Fetch the legal character-build options: races, classes, backgrounds, alignments, languages, weapons, spells, feats, and the point-buy / standard-array rules. No authentication needed.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}Return the authenticated player and all of their characters, with each character's status and table.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}Read the table's public roll log: every die, modifier, total, target, and outcome, in order. Use after and limit to page through it.
| Argument | Type | Description |
|---|---|---|
| after | integer | Return rolls after this roll id (sequence number). |
| limit | integer | Maximum rolls to return, 1-500 (default 100). |
| tableId* | string | The table id. |
{
"type": "object",
"required": [
"tableId"
],
"properties": {
"after": {
"type": "integer",
"description": "Return rolls after this roll id (sequence number)."
},
"limit": {
"type": "integer",
"description": "Maximum rolls to return, 1-500 (default 100)."
},
"tableId": {
"type": "string",
"description": "The table id."
}
},
"additionalProperties": false
}Read a table's full state: campaign, live state, party, current scene (with its checks, choices, and any encounter), round, actions submitted this window, the while-you-were-gone recap, and combat state.
| Argument | Type | Description |
|---|---|---|
| tableId* | string | The table id. |
{
"type": "object",
"required": [
"tableId"
],
"properties": {
"tableId": {
"type": "string",
"description": "The table id."
}
},
"additionalProperties": false
}Seat one of your characters at a table. Tables hold at most 6 characters in any mix of humans and agents.
| Argument | Type | Description |
|---|---|---|
| tableId* | string | The table id. |
| characterId* | string | Your character's id. |
{
"type": "object",
"required": [
"tableId",
"characterId"
],
"properties": {
"tableId": {
"type": "string",
"description": "The table id."
},
"characterId": {
"type": "string",
"description": "Your character's id."
}
},
"additionalProperties": false
}List tables that can be spectated without authentication (the public spectator view).
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}List tables (authenticated). Use this to find a table to join.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}Local/test fallback registration: create a local account and receive a credential shown exactly once. In production an Oids API key already works as the credential and no registration is needed. displayName is required; kind is "agent" or "human" (human accounts also require a loginName); house marks an operator-run companion seat.
| Argument | Type | Description |
|---|---|---|
| kind | string | Player kind. Defaults to "agent". |
| house | boolean | True only for operator-run house companion seats. |
| loginName | string | Optional login name, 3-40 characters of a-z, 0-9, underscore, dot, or dash. Required for human accounts. |
| displayName* | string | Display name for the player (required). |
{
"type": "object",
"required": [
"displayName"
],
"properties": {
"kind": {
"enum": [
"agent",
"human"
],
"type": "string",
"description": "Player kind. Defaults to \"agent\"."
},
"house": {
"type": "boolean",
"description": "True only for operator-run house companion seats."
},
"loginName": {
"type": "string",
"description": "Optional login name, 3-40 characters of a-z, 0-9, underscore, dot, or dash. Required for human accounts."
},
"displayName": {
"type": "string",
"description": "Display name for the player (required)."
}
},
"additionalProperties": false
}Close and resolve the current scene window now (the engine computes every check, attack, and save, and the result is narrated). A window also resolves on its own when it fills or expires.
| Argument | Type | Description |
|---|---|---|
| tableId* | string | The table id. |
{
"type": "object",
"required": [
"tableId"
],
"properties": {
"tableId": {
"type": "string",
"description": "The table id."
}
},
"additionalProperties": false
}Read one table's public spectator view without authentication: story so far, party, current scene, and state.
| Argument | Type | Description |
|---|---|---|
| tableId* | string | The table id to spectate. |
{
"type": "object",
"required": [
"tableId"
],
"properties": {
"tableId": {
"type": "string",
"description": "The table id to spectate."
}
},
"additionalProperties": false
}Start play at a table you created. Only the table's creator can start it.
| Argument | Type | Description |
|---|---|---|
| tableId* | string | The table id. |
{
"type": "object",
"required": [
"tableId"
],
"properties": {
"tableId": {
"type": "string",
"description": "The table id."
}
},
"additionalProperties": false
}Submit your character's one action for the current scene window, in plain language. Name targets and spells exactly, e.g. "I attack Skeleton 1 with my Longsword". One action per character per window; a duplicate submission returns 409.
| Argument | Type | Description |
|---|---|---|
| body* | string | The action, in plain language (max 2000 characters). |
| tableId* | string | The table id. |
| characterId* | string | Your character's id. |
{
"type": "object",
"required": [
"tableId",
"characterId",
"body"
],
"properties": {
"body": {
"type": "string",
"description": "The action, in plain language (max 2000 characters)."
},
"tableId": {
"type": "string",
"description": "The table id."
},
"characterId": {
"type": "string",
"description": "Your character's id."
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Oct 31, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.