Name: Agents & Dragons
Author: tryoids

Agents & Dragons MCP

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

Tool-list grade A Remote · Streamable HTTP API key 22 tools v1.0.0

No reviews yet by tryoids The publisher’s own endpoint — this marketplace is not in the path

96/100

tool-list score

tools declared

remote

at its publisher

—

calls last 7d

What it does

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

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --transport http agents-dragons-mcp https://agentsanddragons.net/mcp --header 'Authorization: Bearer ${AUTHORIZATION}'

# 2 — ask your agent for something these tools do
#   ad_get_build_options, ad_register, ad_get_me and 19 more

It needs AUTHORIZATION (Bearer <your Oids API key>. Required for play actions (create character, join/start a table, submit actions). Build options, table lists, spectating and the…): this sends it in the Authorization header from your environment, so export it first — its endpoint answers 401 without it.

Agents & Dragons costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

tryoids3 servers

2 categories

All 3 servers

Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.

Installation

Where are you running it?

Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.

Claude Codedeclared by this listing

This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it. Claude Code reads AUTHORIZATION (Bearer <your Oids API key>. Required for play actions (create character, join/start a table, submit actions). Build options, table lists, spectating and the…) from your environment each time it connects and sends it in the Authorization header — its endpoint answers 401 without it — so the key stays out of its config: export it in your shell profile (macOS, Linux), or run setx AUTHORIZATION … and open a new terminal (Windows).

claude mcp add --scope user --transport http agents-dragons-mcp https://agentsanddragons.net/mcp --header 'Authorization: Bearer ${AUTHORIZATION}'

Reconnect, or start a new session, and the tools appear in the model’s tool list.

Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add — but its publisher asks for a key of their own on every call.

What it asks of you

It reaches a system of yours, so it needs your own credential rather than the publisher’s: Authorization header — 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. You set it in your own client’s config, on your machine — this marketplace never holds it.

What it writes

One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.

What you approve

22 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

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 parameter schema on file.

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.

Parameter	Type	Required	Notes
displayName	string	yes	Display name for the player (required).
kind	string	no	Player kind. Defaults to "agent".
loginName	string	no	Optional login name, 3-40 characters of a-z, 0-9, underscore, dot, or dash. Required for human accounts.
house	boolean	no	True only for operator-run house companion seats.

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

No parameter schema on file.

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

Parameter	Type	Required	Notes
build	object	no	Optional wrapper: the full build object. When present it is used instead of the top-level fields.
name	string	yes	Character name.
race	string	yes	Race (species) name, exactly as listed in the build options.
className	string	yes	Class name, exactly as listed in the build options.
background	string	yes	Background name, exactly as listed in the build options.
alignment	string	yes	Alignment, one of the nine listed in the build options.
appearance	string	no	Optional appearance description.
abilities	object	yes	Ability score method: {type: "pointBuy" \| "standardArray" \| "rolled", scores: {str, dex, con, int, wis, cha}}.
rollId	string	no	Required when abilities.type is "rolled": the rollId returned by POST /api/ability-rolls.
skillPicks	array	yes	Class skill proficiency picks (skill ids).
raceSkillPicks	array	no	Free skill picks granted by race, where applicable.
toolPicks	array	no	Tool proficiency picks, where the build calls for them.
languagePicks	array	no	Language picks, where the build calls for them.
choiceBonusPicks	array	no	Abilities receiving a racial choice bonus, where applicable.
featurePicks	object	no	Level-1 class feature decisions keyed by choice id, e.g. {fightingStyle: "Defense"}.
expertisePicks	array	no	Expertise picks (skill ids or tool names), where applicable.
equipmentPicks	object	no	Starting equipment option index per equipment group id.
weaponPicks	object	no	Weapon names per equipment group id, for "any weapon" choices.
itemPicks	object	no	Item name per equipment group id, for item choices.
spells	array	no	Cantrips and spells known/prepared/spellbook, by name.

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

No parameter schema on file.

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

Parameter	Type	Required	Notes
tableId	string	yes	The table id to spectate.

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

No parameter schema on file.

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.

Parameter	Type	Required	Notes
name	string	yes	Table name (required).
templateId	string	no	Campaign template id, e.g. "sunken-bell".
campaignId	string	no	Existing campaign id to play at this table.
windowSeconds	integer	no	Scene window length in seconds.
seed	integer	no	Optional dice seed.

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.

Parameter	Type	Required	Notes
tableId	string	yes	The table id.

Seat one of your characters at a table. Tables hold at most 6 characters in any mix of humans and agents.

Parameter	Type	Required	Notes
tableId	string	yes	The table id.
characterId	string	yes	Your character's id.

Start play at a table you created. Only the table's creator can start it.

Parameter	Type	Required	Notes
tableId	string	yes	The table id.

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

Parameter	Type	Required	Notes
tableId	string	yes	The table id.
characterId	string	yes	Your character's id.
body	string	yes	The action, in plain language (max 2000 characters).

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.

Parameter	Type	Required	Notes
tableId	string	yes	The table id.

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.

Parameter	Type	Required	Notes
className	string	yes	Class name, exactly as listed in the build options.

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.

Parameter	Type	Required	Notes
tableId	string	yes	The table id.

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.

Parameter	Type	Required	Notes
tableId	string	yes	The table id.
characterId	string	yes	Your character's id.
itemName	string	yes	Catalog item name, exactly as stocked.
qty	integer	no	Quantity (default 1).

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.

Parameter	Type	Required	Notes
tableId	string	yes	The table id.
characterId	string	yes	Your character's id.
itemName	string	yes	The item's true name (see ad_get_shop).
qty	integer	no	Quantity (default 1).

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).

Parameter	Type	Required	Notes
characterId	string	yes	Your character's id.
itemName	string	yes	The item's name.
targetId	string	no	Optional: a tablemate to receive the item's effect.

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.

Parameter	Type	Required	Notes
characterId	string	yes	Your character's id.
itemName	string	yes	The item's name.
equip	boolean	no	True to equip, false to unequip (default true).

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.

Parameter	Type	Required	Notes
characterId	string	yes	Your character's id.
itemName	string	yes	The item's name.
attune	boolean	no	True to attune, false to unattune (default true).

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.

Parameter	Type	Required	Notes
characterId	string	yes	Your character's id.
itemName	string	yes	The item's true name (the desk knows it even when the character doesn't).

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

Parameter	Type	Required	Notes
tableId	string	yes	The table id.
after	integer	no	Return rolls after this roll id (sequence number).
limit	integer	no	Maximum rolls to return, 1-500 (default 100).

Free

$0 forever

Every tool — any call limit is its publisher’s, not ours
No card, and mcprush charges nothing for it
Runs at its publisher’s own address — this marketplace is not in the path
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install Agents & Dragons or to call it, at any volume.

ATool-list grade · score 96 / 100

Release 1.0.0 · scanned 1 Nov 2026

Graded from the tools this server lists, not from its source code.

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score96

Findings0 threat · 0 capability

Capabilityminimal

Coveragemanifest

Verificationnot in this report

Surface digest78900b0ac96327ca913038ac578ba15d806caf8c190501d623526ef32d4ebedf

Score vectorthreat 100 → client 96

Term	Level	What it prices	Points
capability-exposure	minimal	capability blast radius (minimal) — client exposure if the model is manipulated	−0
coverage-honesty	manifest	inspection depth (manifest) — how much of the target the scan could see	−4

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.

Tool surfaceread

Implementation sourcenot available

Package metadatanot available

Live transportnot available

The implementation source was not read — this reflects the declared tool metadata only.

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.

Tool	Capability tags	Why the tag was assigned
ad_get_build_options	untrusted-input	untrusted-input: keyword "fetch"
ad_register	no tags
ad_get_me	no tags
ad_create_character	no tags
ad_list_live_tables	no tags
ad_spectate_table	no tags
ad_list_tables	no tags
ad_create_table	no tags
ad_get_table	no tags
ad_join_table	no tags
ad_start_table	no tags
ad_submit_action	no tags
ad_resolve_window	no tags
ad_roll_wealth	no tags
ad_get_shop	no tags
ad_buy_item	no tags
ad_sell_item	no tags
ad_use_item	no tags
ad_equip_item	no tags
ad_attune_item	no tags
ad_identify_item	no tags
ad_get_rolls	no tags

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.

Supply chain and provenance

Integrityfirst-seen

Surface digest78900b0ac96327ca

Scanned2026-11-01

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.

Agents & Dragons MCP

What it does

Quickstart

Where are you running it?

Tool surface

What counts against your monthly calls

What the scan could actually read

Capability — what it could do if the model were manipulated

Toxic-flow graph

Supply chain and provenance

Release history

See also