MCP server that wraps the Dagster GraphQL API — manage runs, assets, schedules, sensors, and backfills from any MCP client
Nothing to run from here
Tanod ML 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.
15
tools declared
—
trust score
remote
at its publisher
—
calls last 7d
What it does
Local ML: speech to text (SRT/VTT), text embeddings, reranking, similarity, entities, zero-shot.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http tanod-ml-mcp https://tanod.dev/mcp/ml
# 2 — ask your agent for something these tools do
# embed_texts, rerank_documents, text_similarity and 12 more
Tanod ML costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
TAAll 12 servers
tanod12 servers
10 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 tanod-ml-mcp https://tanod.dev/mcp/mlReconnect, 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
15 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.
mlpeek: Create text embeddings. Returns 384-dimension embeddings of 1-64 texts with bge-small-en-v1.5 (English) or multilingual-e5-small (about 100 languages), normalised by default; input_type applies the model's query or passage prefix. Input: texts, optional model, normalize, encoding and input_type. Each text is cut at the model's 512-token window (truncated says so); over 16,384
| Parameter | Type | Required | Notes |
|---|---|---|---|
| texts | array | yes | 1-64 texts, each at most 8,000 characters; each is truncated at 512 tokens (reported per text). Priced per text, minimum USD 0.001 per call. |
| model | string | no | small-en = BAAI/bge-small-en-v1.5 (English); multilingual = intfloat/multilingual-e5-small (~100 languages). 384 dimensions both. |
| normalize | boolean | no | L2-normalise (cosine similarity = dot product). |
| encoding | string | no | base64 = little-endian float32 bytes. |
| input_type | string | no | Retrieval prefix: query / passage (e5: 'query: ' / 'passage: '; bge: its query instruction / nothing). none = symmetric use. |
mlpeek: Rerank up to 100 documents against a query. Returns 1-100 documents scored against a query by the ms-marco-MiniLM-L6-v2 cross-encoder (Apache-2.0) and sorted best first: index, rank, score (sigmoid of the logit, a relevance in 0-1) and logit; top_k keeps the best k. English model. Input: query, documents, optional top_k. Each text is cut at the model's 512-token window and the answ
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | The query (at most 2,000 characters). |
| documents | array | yes | 1-100 documents, each at most 4,000 characters. |
| top_k | no | Keep the best k (default: all, ranked). |
mlpeek: Score the semantic similarity of one or up to 50 text pairs. Returns the cosine similarity of the embeddings of each text pair (bge-small-en or multilingual-e5-small): one pair as a + b (also a top-level similarity) or 1-50 pairs. Input: a + b, or pairs; each text at most 4,000 characters; optional model. Each text is cut at the model's 512-token window (truncated says so
| Parameter | Type | Required | Notes |
|---|---|---|---|
| a | no | First text of a single pair (at most 4,000 characters). | |
| b | no | Second text of a single pair. | |
| pairs | no | Alternative to a / b: 1-50 {a, b} pairs. Priced per pair, minimum USD 0.001 per call. | |
| model | string | no | small-en (English) or multilingual. |
mlpeek: Extract named entities: people, organisations, places, dates, money, ... Returns named entities in English text with spaCy en_core_web_sm 3.8.0 (MIT): text, label (the 18 OntoNotes types: PERSON, ORG, GPE, LOC, DATE, MONEY, ...) and code-point offsets (end exclusive), plus counts per label; at most 2,000 entities (then entities_truncated). A statistical model: it can miss or mislabel ent
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | English text, at most 20,000 characters. |
| labels | no | Only these entity types (default: all 18 OntoNotes types). |
mlpeek: Classify a text into 1-10 of your labels. Returns scores of 1-10 caller-supplied labels for an English text with the nli-deberta-v3-xsmall NLI cross-encoder (Apache-2.0): single-label scores sum to 1 (softmax over the labels), multi_label scores each label on its own; sorted best first. Scores are model confidences, not calibrated probabilities. Input: text, labels, optional `multi_l
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | English text, at most 2,000 characters. |
| labels | array | yes | 1-10 unique candidate labels, each at most 100 characters. |
| multi_label | boolean | no | Score each label on its own instead of making them compete. |
| hypothesis_template | string | no | Must contain {} exactly once. |
utilpeek: Analyze the sentiment of an English text. Returns VADER sentiment of an English text: compound (-1 to 1), positive / neutral / negative shares and a label (positive at 0.05 or more, negative at -0.05 or less), optionally per sentence. A lexicon heuristic: it misses sarcasm and domain jargon. Input: text and optional per_sentence. Typically under 1 s. Price: USD 0.001. Free: 10 utilpe
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | The text (at most 200,000 characters). |
| per_sentence | boolean | no | Also score each sentence (default false: whole text only). |
utilpeek: Extract the keywords and keyphrases of a text. Returns the top keyphrases of a text by RAKE (phrases between stop words and punctuation, scored by word degree / frequency), with score and count. Input: text, optional language, top_n and max_words. Typically under 0.3 s. Price: USD 0.002. Free: 10 utilpeek calls per IP per UTC day. Tanod does not log or store the submitted text; i
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | The text (at most 200,000 characters). |
| language | string | no | Stop-word language: de, en (default), es, fr, it, nl or pt. |
| top_n | integer | no | Keyphrases to return, best first (1-100, default 10). |
| max_words | integer | no | Longest keyphrase, in words. |
utilpeek: Summarize a text by picking its key sentences. Returns an extractive summary: the most central sentences (or ratio of them) by LexRank, picked verbatim and kept in their original order, with per-sentence scores. It does not paraphrase, shorten or check facts. Input: text, optional language, sentences or ratio. Typically under 0.5 s. Price: USD 0.003. Free: 10 utilpeek calls p
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | The text (at most 200,000 characters). |
| language | string | no | Stop-word language: de, en (default), es, fr, it, nl or pt. |
| sentences | integer | no | Sentences to pick (ignored when ratio is set). |
| ratio | no | Pick this share of the sentences instead (at most 100). |
utilpeek: Detect the language of a text. Returns the most likely language (ISO 639-1 and 639-3 code, name, confidence) and 3 alternatives, from an offline ensemble of lingua (Apache-2.0) and langid.py (BSD-2-Clause) over 75 languages; reliable is true only with at least 20 letters and confidence 0.6 or more. Input: text. Short text is often flagged unreliable; text with no letters is a 422 no_
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | The text (at most 20,000 characters). |
mlpeek: Speech to text and subtitles: transcribe audio to text, timed segments, SRT and WebVTT. Returns the transcript of an audio file (MP3, WAV, FLAC, OGG, Opus, M4A/AAC, WebM, MP4 audio) of up to 10 minutes and 25 MB: text, language, duration, timed segments and srt / vtt caption strings (faster-whisper, int8 base model); translate_to_english gives English text and captions. Input
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | no | Public http(s) URL of the audio file (at most 25 MB; private, internal and IP-literal hosts are refused); or use file_base64. | |
| file_base64 | no | The audio file as base64 (at most 25 MB decoded); or use url. MP3, WAV, FLAC, OGG, Opus, M4A/AAC, WebM and MP4 audio, detected from the content. At most 10 minutes. | |
| language | no | Optional spoken language as an ISO 639-1 code (en, es, fr, de, tl, ...). Default: detected from the first 30 seconds. | |
| translate_to_english | boolean | no | true: the text, segments, srt and vtt come out in English from any spoken language (Whisper translate task); language is still the spoken language. Default false: the text stays in the spoken langua |
mlpeek: Transcribe a podcast episode from its RSS feed: a window of up to 10 minutes as text, timed segments, SRT. Returns a transcript window (up to 10 min from start_s) of a podcast episode picked from its RSS feed: text, language, timed segments, srt and vtt with episode times, and window.next_start_s. Input: feed_url, optional episode selector, start_s, duration_s, language, `translate
| Parameter | Type | Required | Notes |
|---|---|---|---|
| feed_url | string | yes | Public http(s) URL of the show's RSS feed (find it with /v1/podcast/search). |
| guid | no | Pick the episode by its feed guid. Use at most one of guid, episode_number and episode_title; none picks the latest episode with audio. | |
| episode_number | no | Pick the episode by its itunes:episode number. | |
| season | no | With episode_number: the itunes:season number. | |
| episode_title | no | Pick the newest episode whose title contains this text (case-insensitive; an exact title wins). | |
| start_s | number | no | Where the window starts, in seconds from the beginning of the episode (default 0). |
| duration_s | integer | no | Window length in seconds, 5-600 (default 600, the 10-minute limit of one call). |
| language | no | Optional spoken language as an ISO 639-1 code (default: detected). | |
| translate_to_english | boolean | no | true: text, segments, srt and vtt in English (Whisper translate). Same price. |
mlpeek: Translate text between English and 14 languages. Returns the text translated between English and es, fr, de, pt, it, nl, ru, zh, ja, ko, ar, hi, id or tl (other pairs pivot through English): text, source_lang (detected when you omit source, then detected is true), target_lang, chars, engine. Offline neural MT: quality is below large commercial engines. Input: text, target
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | The text to translate, at most 5,000 characters. |
| target | string | yes | Target language, ISO 639-1: en, es, fr, de, pt, it, nl, ru, zh, ja, ko, ar, hi, id or tl. |
| source | no | Source language, same codes. Omit it to detect the language (the reply then has detected: true). |
mlpeek: Check text for prompt injection before an agent acts on it. Returns a verdict, a score (0-1; injection at 0.9 and above) and chunks, the flagged sentences with score and offsets. A small open classifier (DeBERTa-v3), automated and heuristic: it can miss new attacks and flag harmless text. Input: text. At most 20,000 characters; English-first. Over the token budget is a 422 and an
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | The text to screen, 1 to 20,000 characters: a web page, an email or a tool result an agent is about to act on. |
mlpeek: Speak text aloud in 41 voices: English, Spanish, French, Hindi, Italian, Portuguese. Returns the text spoken as audio: data_base64 (mp3, wav or ogg), content_type, bytes, duration_s, sample_rate, voice, speed. Offline neural TTS (Kokoro-82M); the audio is a synthetic voice. Input: text, optional voice, speed, format. At most 2,000 characters; 41 voices in 6 languages
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Text to speak, 1 to 2,000 characters, in the language of the chosen voice (English, Spanish, French, Hindi, Italian or Brazilian Portuguese). |
| voice | string | no | Voice (41): the first letter is the language: a US English (af_heart default, af_bella, am_adam), b UK English (bf_emma, bm_george), e Spanish (ef_dora), f French (ff_siwis), h Hindi (hf_alpha, hm_ome |
| speed | number | no | Speaking rate, 0.5 to 2.0 (1.0 is normal). |
| format | string | no | Audio format: mp3, wav (16-bit PCM) or ogg (Opus). |
| output | string | no | base64 (default): the file comes back inline as base64. url: the file is stored for 24 hours and the reply carries a download link (url, expires_at, bytes, content_type, sha256) instead of the base64, |
mlpeek: Translate speech: audio to English or 14 languages, optionally spoken. Returns speech translation of an audio file of up to 2 minutes: the language is detected and the speech returned as text in target (en, es, fr, de, pt, it, nl, ru, zh, ja, ko, ar, hi, id, tl) with timed segments, optionally a transcript and, with speak (en, es, fr, hi, it, pt; clip at most 45 s), spoken audio. I
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | no | Public http(s) URL of the audio file (at most 25 MB; private, internal and IP-literal hosts are refused); or use file_base64. | |
| file_base64 | no | The audio file as base64 (at most 25 MB decoded); or use url. At most 2 minutes (45 seconds with speak). | |
| target | string | yes | Language of the translation: en (one Whisper pass) or es, fr, de, pt, it, nl, ru, zh, ja, ko, ar, hi, id, tl (Whisper to English, then English to the target). |
| language | no | Optional spoken language as an ISO 639-1 code. Default: detected. | |
| include_transcript | boolean | no | true adds transcript in the spoken language with a second Whisper pass (about doubles the speech-to-text time). English audio always returns it. |
| speak | boolean | no | true adds audio, the translation spoken (Kokoro). Targets en, es, fr, hi, it and pt only; the clip is limited to 45 seconds and at most 800 characters are spoken. |
| voice | no | With speak: a voice for the target language (default af_heart en, ef_dora es, ff_siwis fr, hf_alpha hi, if_sara it, pf_dora pt). | |
| format | string | no | With speak: mp3, wav or ogg. |
| output | string | no | base64 (default): the file comes back inline as base64. url: the file is stored for 24 hours and the reply carries a download link (url, expires_at, bytes, content_type, sha256) instead of the base64, |
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 Tanod ML 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: —
—Grade not published
No rule-by-rule report on file for this release
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.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither. So there is no grade — not a withheld one, an unmeasured one.
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 0.1.1.
0.1.1
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 Tanod ML 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.