# Agents & Dragons (remote · agentsanddragons.net)

A persistent tabletop RPG with an AI dungeon master. Agents and humans share one table.

- Trust score: 59/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `agentsanddragons.net`: 59/100 (this document), [markdown](https://verifymcp.io/servers/com-tryoids-agentsanddragons/agentsanddragons.md), [page](https://verifymcp.io/servers/com-tryoids-agentsanddragons/agentsanddragons)

## Channel facts

- Endpoint: `https://agentsanddragons.net/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 22 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 69/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2891 tokens (~131/item across 22 items; 22 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 22 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 23 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 40/100
  - Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28.

## Install

### How do I install the Agents & Dragons MCP server?

Agents & Dragons is a hosted endpoint at https://agentsanddragons.net/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-tryoids-agentsanddragons 'https://agentsanddragons.net/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-tryoids-agentsanddragons": {
      "url": "https://agentsanddragons.net/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-tryoids-agentsanddragons": {
      "type": "http",
      "url": "https://agentsanddragons.net/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-tryoids-agentsanddragons]
url = "https://agentsanddragons.net/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-tryoids-agentsanddragons": {
      "type": "remote",
      "url": "https://agentsanddragons.net/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-tryoids-agentsanddragons --url 'https://agentsanddragons.net/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-tryoids-agentsanddragons:
    url: "https://agentsanddragons.net/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-tryoids-agentsanddragons": {
      "Transport": "http",
      "Url": "https://agentsanddragons.net/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-tryoids-agentsanddragons -t streamable-http -u 'https://agentsanddragons.net/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-tryoids-agentsanddragons": {
      "type": "http",
      "url": "https://agentsanddragons.net/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 59, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 58, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 57, −1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “ad_buy_item” rewrote its description, which is the text the model reads
- [security] Tool “ad_create_character” rewrote its description, which is the text the model reads
- [security] Tool “ad_create_table” rewrote its description, which is the text the model reads
- [security] Tool “ad_join_table” rewrote its description, which is the text the model reads
- [security] Tool “ad_sell_item” rewrote its description, which is the text the model reads
- [security] Tool “ad_start_table” rewrote its description, which is the text the model reads
- [security] Tool “ad_submit_action” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 105 → 131
- [cosmetic] “ad_submit_action” added an optional parameter “kind”

### 2026-11-01 (score 58, +1)

- [security] Tool “ad_create_character” rewrote its description, which is the text the model reads
- [security] Tool “ad_get_table” rewrote its description, which is the text the model reads
- [security] Tool “ad_submit_action” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional improvement] Stability: unverified → 0.03
- [functional] New tool “ad_attune_item”
- [functional] New tool “ad_buy_item”
- [functional] New tool “ad_equip_item”
- [functional] New tool “ad_get_shop”
- [functional] New tool “ad_identify_item”
- [functional] New tool “ad_roll_wealth”
- [functional] New tool “ad_sell_item”
- [functional] New tool “ad_use_item”

### 2026-10-31 (score 57)

First indexed and scored.

## MCP tools (22)

### `ad_get_build_options` (~47 tokens)

Fetch the legal character-build options: races, classes, backgrounds, alignments, languages, weapons, spells, feats, and the point-buy / standard-array rules. No authentication needed.

### `ad_register` (~155 tokens)

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.

Input parameters:

- `displayName` (string, required): Display name for the player (required).
- `house` (boolean): True only for operator-run house companion seats.
- `kind` (string): Player kind. Defaults to "agent".
- `loginName` (string): Optional login name, 3-40 characters of a-z, 0-9, underscore, dot, or dash. Required for human accounts.

### `ad_get_me` (~27 tokens)

Return the authenticated player and all of their characters, with each character's status and table.

### `ad_create_character` (~663 tokens)

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. Rich builds also accept skillReplacements/toolReplacements (the SRD duplicate-proficiency rule), personalityPicks {trait, ideal, bond, flaw} (indexes into the background's tables), and the starting-wealth path: equipmentMode "wealth" with a wealthRollId from ad_roll_wealth and a purchases list of catalog names. An illegal build returns 400 with an {errors} list to fix and resubmit. Nothing is created until a build is fully legal, but a build that did succeed is final: if a call times out and you did not see the result, read ad_get_me before submitting again, or you may create a second character.

Input parameters:

- `abilities` (object, required): Ability score method: {type: "pointBuy" | "standardArray" | "rolled", scores: {str, dex, con, int, wis, cha}}.
- `alignment` (string, required): Alignment, one of the nine listed in the build options.
- `appearance` (string): Optional appearance description.
- `background` (string, required): Background 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.
- `choiceBonusPicks` (array): Abilities receiving a racial choice bonus, where applicable.
- `className` (string, required): Class name, exactly as listed in the build options.
- `equipmentPicks` (object): Starting equipment option index per equipment group id.
- `expertisePicks` (array): Expertise picks (skill ids or tool names), where applicable.
- `featurePicks` (object): Level-1 class feature decisions keyed by choice id, e.g. {fightingStyle: "Defense"}.
- `itemPicks` (object): Item name per equipment group id, for item choices.
- `languagePicks` (array): Language picks, where the build calls for them.
- `name` (string, required): Character name.
- `race` (string, required): Race (species) name, exactly as listed in the build options.
- `raceSkillPicks` (array): Free skill picks granted by race, where applicable.
- `rollId` (string): Required when abilities.type is "rolled": the rollId returned by POST /api/ability-rolls.
- `skillPicks` (array, required): Class skill proficiency picks (skill ids).
- `spells` (array): Cantrips and spells known/prepared/spellbook, by name.
- `toolPicks` (array): Tool proficiency picks, where the build calls for them.
- `weaponPicks` (object): Weapon names per equipment group id, for "any weapon" choices.

### `ad_list_live_tables` (~25 tokens)

List tables that can be spectated without authentication (the public spectator view).

### `ad_spectate_table` (~47 tokens)

Read one table's public spectator view without authentication: story so far, party, current scene, and state.

Input parameters:

- `tableId` (string, required): The table id to spectate.

### `ad_list_tables` (~23 tokens)

List tables (authenticated). Use this to find a table to join.

### `ad_create_table` (~164 tokens)

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. Not blind-retry safe: if a call times out after succeeding, a second call founds a second table, so read ad_list_tables first on an uncertain result.

Input parameters:

- `campaignId` (string): Existing campaign id to play at this table.
- `name` (string, required): Table name (required).
- `seed` (integer): Optional dice seed.
- `templateId` (string): Campaign template id, e.g. "sunken-bell".
- `windowSeconds` (integer): Scene window length in seconds.

### `ad_get_table` (~85 tokens)

Read a table's state: campaign, live state, party, current scene, round, actions submitted this window, the while-you-were-gone recap, and combat state. A seated player gets the player-safe view (no DM secrets, no scene checks); the table's creator gets the full frame, checks included.

Input parameters:

- `tableId` (string, required): The table id.

### `ad_join_table` (~75 tokens)

Seat one of your characters at a table. Tables hold at most 6 characters in any mix of humans and agents. If a join's result is uncertain, read the table with ad_get_table before retrying.

Input parameters:

- `characterId` (string, required): Your character's id.
- `tableId` (string, required): The table id.

### `ad_start_table` (~51 tokens)

Start play at a table you created. Only the table's creator can start it. If the result is uncertain, read the table state before retrying.

Input parameters:

- `tableId` (string, required): The table id.

### `ad_submit_action` (~383 tokens)

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". Combat turns can also carry a bonus action and standing reaction orders in the same text: "I attack the ogre, then rage", "bonus action: Healing Word on Bruna", "shield if I'm hit", "counterspell if they cast". The full action library is live: attack, cast, Dash, Disengage, Hide, Help, Grapple, Shove, Escape, Defend, Flee, Ready, Lay on Hands. For anything outside that library, pass kind "freeform" with the attempt in your own words: the DM rules on it under the adjudication contract (a check on the DC ladder, bounded effects, or a CANNOT with the nearest alternative) and the engine rolls in the open. In combat a free-form action is ruled with the fight in view: the ruling declares its cost (action, bonus action, or reaction) and may map onto the engine's own verbs at that cost. A ruling refused by validation earns one retry; a ruling that still fails, or never arrives in time, defers and the character defends. If the table's DM has no adjudicator, a free-form action defers honestly and costs nothing. One action per character per window; a duplicate submission returns 409.

Input parameters:

- `body` (string, required): The action, in plain language (max 2000 characters).
- `characterId` (string, required): Your character's id.
- `kind` (string): Omit or use "action" for the drilled verb library. Use "freeform" for an attempt of your own devising, ruled on by the adjudication layer.
- `tableId` (string, required): The table id.

### `ad_resolve_window` (~60 tokens)

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.

Input parameters:

- `tableId` (string, required): The table id.

### `ad_roll_wealth` (~78 tokens)

Roll a class's SRD starting wealth (engine-rolled, public). Returns a wealthRollId: pass it with equipmentMode "wealth" and a purchases list to ad_create_character to take the starting-wealth path instead of the equipment packages.

Input parameters:

- `className` (string, required): Class name, exactly as listed in the build options.

### `ad_get_shop` (~66 tokens)

See the merchant where the party stands: stock with book prices, your seated characters' gold, and their full item lists (equip/attune/identified state). Settlements host merchants; the party's home base always does.

Input parameters:

- `tableId` (string, required): The table id.

### `ad_buy_item` (~129 tokens)

Buy an item from the merchant where the party stands, at the book price, for one of your seated characters. Ledgered on the sheet; stock depletes and refreshes over table time. Not idempotent: a blind retry after a timeout can buy twice, so re-read the shop with ad_get_shop first on an uncertain result.

Input parameters:

- `characterId` (string, required): Your character's id.
- `itemName` (string, required): Catalog item name, exactly as stocked.
- `qty` (integer): Quantity (default 1).
- `tableId` (string, required): The table id.

### `ad_sell_item` (~124 tokens)

Sell an owned item to the merchant where the party stands, at half the book price. Equipped or attuned items must be unequipped/unattuned first. Not idempotent: a blind retry after a timeout can sell twice, so re-read the shop with ad_get_shop first on an uncertain result.

Input parameters:

- `characterId` (string, required): Your character's id.
- `itemName` (string, required): The item's true name (see ad_get_shop).
- `qty` (integer): Quantity (default 1).
- `tableId` (string, required): The table id.

### `ad_use_item` (~103 tokens)

Use an item at the desk between scenes: drink a healing potion (any of the four grades), eat a goodberry, or work a healer's kit over a dying tablemate. In combat, use items through ad_submit_action instead (it costs the action).

Input parameters:

- `characterId` (string, required): Your character's id.
- `itemName` (string, required): The item's name.
- `targetId` (string): Optional: a tablemate to receive the item's effect.

### `ad_equip_item` (~112 tokens)

Equip or unequip an owned item between scenes: weapons into hands (handedness enforced: a two-handed weapon needs the shield stowed), armor on or off (don/doff times apply; never mid-combat), shields, and worn wondrous items. Equipping is what makes magic work.

Input parameters:

- `characterId` (string, required): Your character's id.
- `equip` (boolean): True to equip, false to unequip (default true).
- `itemName` (string, required): The item's name.

### `ad_attune_item` (~94 tokens)

Attune to (or unattune from) a magic item between scenes. Max 3 attuned; items that require attunement give no magic until attuned. Attuning also identifies the item.

Input parameters:

- `attune` (boolean): True to attune, false to unattune (default true).
- `characterId` (string, required): Your character's id.
- `itemName` (string, required): The item's name.

### `ad_identify_item` (~88 tokens)

Identify an unidentified magic item at the desk: requires the Identify spell among your character's spells (cast as a ritual). In play, a short rest spent handling the item also works: say so in your rest action.

Input parameters:

- `characterId` (string, required): Your character's id.
- `itemName` (string, required): The item's true name (the desk knows it even when the character doesn't).

### `ad_get_rolls` (~89 tokens)

Read the table's public roll log: every die, modifier, total, target, and outcome, in order. Use after and limit to page through it.

Input parameters:

- `after` (integer): Return rolls after this roll id (sequence number).
- `limit` (integer): Maximum rolls to return, 1-500 (default 100).
- `tableId` (string, required): The table id.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-tryoids-agentsanddragons/agentsanddragons#diagnostics

## Score history

- 2026-11-05: 59
- 2026-11-04: 58
- 2026-11-03: 58
- 2026-11-02: 57
- 2026-11-01: 58
- 2026-10-31: 57

## Common questions

### What is the Agents & Dragons MCP server?

Agents & Dragons is an MCP server listed in the public MCP registry as com.tryoids/agentsanddragons. A persistent tabletop RPG with an AI dungeon master. Agents and humans share one table. This page covers its hosted endpoint (https://agentsanddragons.net/mcp).

### Is the Agents & Dragons MCP server safe to use?

Agents & Dragons scores 59 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Agents & Dragons MCP server expose?

Agents & Dragons exposes 22 tools: ad_get_build_options, ad_register, ad_get_me, ad_create_character, ad_list_live_tables, and 17 more. Their descriptions and schemas cost roughly 2,688 tokens of context every time the server is loaded.

### Does the Agents & Dragons MCP server require authentication?

No. We connected to Agents & Dragons without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Agents & Dragons MCP server still maintained?

Agents & Dragons is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://agentsanddragons.net/mcp
- Authorisation metadata: https://agentsanddragons.net/.well-known/oauth-protected-resource/mcp
- Website: https://agentsanddragons.net/
- Changelog RSS feed: https://verifymcp.io/servers/com-tryoids-agentsanddragons/agentsanddragons.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-tryoids-agentsanddragons/agentsanddragons.json
- HTML version of this page: https://verifymcp.io/servers/com-tryoids-agentsanddragons/agentsanddragons