RU
Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.
Nothing to run from here
NodNod is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
90/100
tool-list score
23
tools declared
remote
at its publisher
—
calls last 7d
What it does
Give your agent a face, a voice and a brain, then send it to a meeting or its own web page.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http nodnod-mcp https://api.nodnod.ai/mcp
# 2 — ask your agent for something these tools do
# sign_up, verify_owner, resend_owner_letter and 20 more
NodNod costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
PHAll 2 servers
phoneburner2 servers
2 categories
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 mcp add --scope user --transport http nodnod-mcp https://api.nodnod.ai/mcpReconnect, 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.
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
23 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.
Open to any agent. Creates a trial account owned by the human at owner_email and returns an API key (shown once) that works at once: create_nod, test_nod, list_parts, create_key and revoke_key all work now. NodNod sends the owner ONE email with a one-click confirm link and a six digit code as a backup. When they press the link (or give you the code for verify_owner) you can also send Nods and spen
| Parameter | Type | Required | Notes |
|---|---|---|---|
| owner_email | string | yes | The human who will be accountable for this account. NodNod emails them one confirm link. |
| display_name | string | no | Your owner's name, shown on the personal page ("An AI agent put here by <name>"). Left out, the page says "its owner". |
| handle | string | no | The personal page path, <web>/<handle> (get_account and send_nod give the full address). Made up if left out. |
| key_label | string | no | — |
The backup to the one-click link: pass the six digit code your owner read from the NodNod email. On success the trial ends and your key can send Nods and spend. Five wrong tries closes the code; then call resend_owner_letter. Tries are also limited per key and per account (10 an hour, 20 a day). If the owner pressed the link instead, get_account shows is_verified true and you need not call this.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| code | string | yes | — |
Sends a fresh code and link to the owner (the old ones stop working). At most 3 an hour and 6 a day.
No parameter schema on file.
Shows whether the owner has verified, your handle, and the scopes this key holds right now.
No parameter schema on file.
The face, voice and brain ids create_nod and update_nod accept, and the default for each.
No parameter schema on file.
The photoreal Anam avatars on NodNod's own account that this account may use (most accounts: none yet). For an avatar on your own Anam account, see "note".
No parameter schema on file.
Every Nod on the account that has not been deleted.
No parameter schema on file.
One Nod by id.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
Makes a new Nod. Only name is required; parts left out use "default". It starts private. A trial account may hold 3 Nods. space "team" makes it in your team's space (teams only).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| personality | string | no | Who the Nod is and how it talks, in plain words. |
| face | string | no | A face id from list_parts, or "default". |
| face_id | string | no | The avatar for the outside-anam face: your own Anam avatar id (your Anam key, added in Studio, pays), or a nodnod: id from list_faces. "" for none. |
| voice | string | no | A voice id from list_parts, or "default". |
| voice_id | string | no | The voice inside the voice part, from list_parts or the catalogue (am_fenrir, bf_emma...). "" for its default. |
| brain | string | no | A brain id from list_parts, or "default". |
| brain_tier | string | no | fast (the default) or big. |
| abilities | array | no | Built-in abilities to switch on. |
| slug | string | no | The last part of the page address, <web>/<handle>/<slug>. Made from the name if left out. |
| space | string | no | "personal" (the default): yours, and it goes where you go. "team": made in your team's space; it stays with the team if you leave, and a team key is revoked when you do. |
Changes only the fields you pass. Set is_paused true to stop it being sent anywhere.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
| name | string | no | — |
| personality | string | no | Who the Nod is and how it talks, in plain words. |
| face | string | no | A face id from list_parts, or "default". |
| face_id | string | no | The avatar for the outside-anam face: your own Anam avatar id (your Anam key, added in Studio, pays), or a nodnod: id from list_faces. "" for none. |
| voice | string | no | A voice id from list_parts, or "default". |
| voice_id | string | no | The voice inside the voice part, from list_parts or the catalogue (am_fenrir, bf_emma...). "" for its default. |
| brain | string | no | A brain id from list_parts, or "default". |
| brain_tier | string | no | fast (the default) or big. |
| abilities | array | no | Built-in abilities to switch on. |
| slug | string | no | The last part of the page address, <web>/<handle>/<slug>. Made from the name if left out. |
| is_paused | boolean | no | — |
Removes the Nod from the account and its page. Its history is kept for the owner.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
Sends one message to your Nod and returns its answer, using its name, personality and brain. Works right after create_nod, before your owner verifies. Pass history (earlier turns, oldest first, each { role: "user" or "assistant", text }; the field is text, not content) to test a short conversation. Free, up to 30 turns a day in trial and 300 after. It is a text test of the brain and personality; t
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
| text | string | yes | — |
| history | array | no | — |
to "page" opens the Nod's personal page to visitors (after an automatic leak check) and returns its URL and the embed code; pass embed_origins to let other websites show it. to "meeting" with meeting_url (Zoom, Teams, Meet or Webex) sends it into that call. to "meetingburner_room" with meeting_url (a MeetingBurner room link) sends it into the room as a member with its face and voice, on your own M
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
| to | string | yes | — |
| meeting_url | string | no | — |
| meetingburner_key | string | no | Your MeetingBurner outside agent key. Needed once; it is kept in a vault and never shown again. |
| audience | string | no | Who may talk to the page: "public" (anyone, the default) or "invited". |
| embed_origins | array | no | Websites that may show the embed, e.g. ["https://example.com"]. Left out keeps the current list. |
Starts the Nod in a fresh room on our GPU, paid from your balance, and returns the room address and a pass that joins it with a microphone (LiveKit). The Nod says it is an AI agent, then answers. It leaves when you stop it, when the room is empty for a minute, or where your credit ends.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
| seconds | integer | no | — |
Whether the Nod is still in the room, why it left, and what it cost once settled.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
Asks the Nod to leave its room now, waits a few seconds for it to go, and returns the final state and cost.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
Every key on your account, live and revoked. Secrets are never shown; prefix tells keys apart and is_this_key marks the one you are calling with.
No parameter schema on file.
Makes a new key on your own account, for example a narrower one for a helper. scopes defaults to the calling key's scopes and may never be wider. Works in trial (up to 5 live keys); while the owner has not verified, every key is still cut to trial scopes. The secret is returned once: store it. space "team" makes a team key (teams only): it is revoked if you leave the team.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| label | string | yes | — |
| scopes | array | no | — |
| space | string | no | "personal" (the default): yours, and it goes where you go. "team": made in your team's space; it stays with the team if you leave, and a team key is revoked when you do. |
The key stops working at once, on REST and MCP. Only keys on your own account can be revoked. Revoking the key you are calling with is allowed and ends your access, so make a new key first if you need one.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
Money available for running Nods, in micro-dollars (1 USD = 1,000,000) and as dollars, with one plain line that says why when it is zero.
No parameter schema on file.
Answers a Stripe TEST-mode Checkout link for one credit pack: pack-10 ($10 of credit), pack-25 ($25 of credit), pack-100 ($100 of credit). You do not pay: give the link to your owner, who opens it and pays (in test mode the card 4242 4242 4242 4242 with any future date works). amount_usd is the credit the pack adds; price_usd is what your owner pays for it on their plan today (less on a paid plan)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pack_id | string | yes | One of: pack-10 ($10 of credit), pack-25 ($25 of credit), pack-100 ($100 of credit). |
API calls by operation and sends by target over the last N days (default 30).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| days | integer | no | — |
If you already have a NodNod API key (from an earlier sign_up or create_key), pass it here once and the rest of this connection uses it. Not needed right after sign_up, which attaches its key for you.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| api_key | string | yes | A key starting nod_sk_. |
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
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install NodNod or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 90 / 100
Release 0.1.0 · scanned 9 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 score90
Findings0 threat · 2 capability
Capabilityhigh
Coveragemanifest
Verificationnot in this report
Surface digest8ba6b2fe2940296f5990e9b4d49e0b2f0525efec1d2fdb39ae3d7396d8229e01
Score vectorthreat 100 → client 90
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| 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. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| sign_up | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| verify_owner | state-write | state-write: declares readOnlyHint: false |
| resend_owner_letter | state-write | state-write: declares readOnlyHint: false |
| get_account | no tags | |
| list_parts | no tags | |
| list_faces | no tags | |
| list_nods | no tags | |
| get_nod | no tags | |
| create_nod | state-write | state-write: declares readOnlyHint: false |
| update_nod | state-write | state-write: declares readOnlyHint: false |
| delete_nod | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| test_nod | state-write | state-write: declares readOnlyHint: false |
| send_nod | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| start_session | state-write | state-write: declares readOnlyHint: false |
| get_session | no tags | |
| stop_session | state-write | state-write: declares readOnlyHint: false |
| list_keys | sensitive-source | sensitive-source: keyword "list_keys" |
| create_key | state-write | state-write: declares readOnlyHint: false |
| revoke_key | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| get_balance | no tags | |
| top_up | state-write | state-write: declares readOnlyHint: false |
| get_usage | no tags | |
| use_key | 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.
list_keys → send_nod
A sensitive-source → external-sink chain exists: list_keys → send_nod.
Supply chain and provenance
Integrityfirst-seen
Surface digest8ba6b2fe2940296f
Scanned2026-11-09
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.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 0.1.0.
0.1.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish NodNod can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.