Atlas entry

`gateway.pipeworx.io`

47 capabilities over MCP. The inventory is incomplete. First atlas observation.

Observed 12 Nov 2026, 13:04 UTC · passive: no tools called, no credentials sent · sha256:25bf12…b1f4

47 tools. 18 only read. 3 change records, and 2 of those delete or cancel. 26 have no reading.

AI reading, beta. side-effects v1 on claude-haiku-5.5, calibrated on MCP (golden-3). Only readings above a measured precision count. Counts are tools, not calls: no tool was called.

AI readings summary · beta

The service lists 47 tools, and 21 have AI readings.

forget and unsubscribe are read as deleting or cancelling records.

subscribe is read as creating records.

18 tools are read as read-only, including prediction_calibration, release_calendar_markets and compare_entities.

Written by code from the AI readings on this page: it groups them and says nothing they do not.

What an agent can do here

AI readings, beta · Readings on 21 of 47 MCP tools. 2 read as deleting or cancelling.

Moves money
0
No tool read this way.
Deletes or cancels records
2 tools
- forget0.90
- unsubscribe0.85
Sends messages to people
0
No tool read this way.
Changes permissions
0
No tool read this way.
Runs code
0
No tool read this way.
Should ask a person first
0
No tool read this way.

No counted reading 26 tools No reading was counted, so any effect above is possible for them: ai_visibility_check, archive_compare, archive_evidence, ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, classify_row, discover_tools, email_finder, email_verifier and 16 more.

What changed

First atlas observation. Atlas history

Look first

AI reading, beta: AI adds items here; it never removes one.

forgetDeletes or cancels records · 0.90
unsubscribeDeletes or cancels records · 0.85

Surfaces

5 protocols checked

ARD	unreachable	No document retrieved
A2A	invalid	0 skills
MCP	Valid	2025-03-26 · 47 tools · 0 resources retained · listing incomplete · 0 prompts retained · listing incomplete
OpenAPI	Not detected	0 operations
WebMCP	Not detected	0 declarative form tools · experimental

Exact states and meaning

ARD
failed
Exact state: unreachable · No document retrieved
The supported discovery location did not provide a usable response within the observation boundary.
An unreachable result does not prove the service is unavailable to every client or that it advertises no capabilities.
Not observed / not fetched
A2A
failed
Exact state: invalid · Revision 1.0 · 0 skills
InterfaceDelta retained the machine state “invalid” without assigning an additional meaning.
Not observed / not fetched
MCP
observed
Exact state: valid · Revision 2025-03-26 · 47 tools · 0 resources retained · listing incomplete · 0 prompts retained · listing incomplete
A usable protocol document was retrieved and validated.
Directly observed
OpenAPI
absent
Exact state: not detected · 0 operations
No endpoint was established from the evidence and scope that InterfaceDelta inspected.
Not detected does not prove that no endpoint exists.
Not observed / not fetched
WebMCP
absent
Exact state: not detected · 0 declarative form tools · experimental
No named declarative WebMCP form tools were observed in the origin root HTML.
Script-registered tools and other pages are not observed, so this does not mean the site has no WebMCP tools.
Not observed / not fetched

47 · inventory incomplete

Showing 47 of 47.

Tool and inputs							◇ AI reading, beta · confidence
Read as one of the six effects 2 AI only raises attention: these rows come first.
◇ AI Deletes a saved memory entry identified by its key, permanently removing it from the agent's storage.k, key*, label, name◇ AIDeletes or cancels records 0.90		Deletes or cancels records 0.90					Deletes or cancels records0.90
`forget` inputs `k`, `key` (required), `label`, `name` AI Deletes or cancels records 0.90
◇ AI Cancels a subscription by its ID, deactivating it while keeping its past events available for later viewing.id*◇ AIDeletes or cancels records 0.85		Deletes or cancels records 0.85					Deletes or cancels records0.85
`unsubscribe` inputs `id` (required) AI Deletes or cancels records 0.85
Read as none of the six 19 Not a clearance.
◇ AI Returns an evidence packet and market-vs-model edge comparison for a Polymarket bet, given a market slug, URL, or question.depth, include_raw, market*							Reads only0.85
`bet_research` inputs `depth`, `include_raw`, `market` (required) AI Reads only 0.85
◇ AI Returns one financial metric for a US listed firm's specified fiscal period, with its source filing and derivation flag.as_of, attribute, basis, company and 5 more							Reads only0.86
`company_facts` inputs `as_of`, `attribute` (required), `basis`, `company` (required) and 5 more AI Reads only 0.86
◇ AI Returns official registered company matches from national business registers by name, with each register's ID and as-of date.country, limit, name*							Reads only0.82
`company_register_search` inputs `country`, `limit`, `name` (required) AI Reads only 0.82
type, values							Reads only0.88
`compare_entities` inputs `type` (required), `values` (required) AI Reads only 0.88
◇ AI Returns a cited findings packet answering multi-part questions by querying many structured data sources in parallel.ask, depth, input, message and 5 more							Reads only0.80
`deep_research` inputs `ask`, `depth`, `input`, `message` and 5 more AI Reads only 0.80
◇ AI Returns work email contacts for a given domain, with names, job titles, departments, confidence scores and the address pattern.department, domain*, limit, type and 1 more							Reads only0.80
`domain_search` inputs `department`, `domain` (required), `limit`, `type` and 1 more AI Reads only 0.80
backtest_days, city, date, market_type and 1 more							Reads only0.80
`kalshi_weather_edge` inputs `backtest_days`, `city`, `date`, `market_type` and 1 more AI Reads only 0.80
◇ AI Lists your active subscriptions with their ids, types, timestamps and fire counts, optionally including inactive ones.include_inactive							Reads only0.88
`list_subscriptions` inputs `include_inactive` AI Reads only 0.88
◇ AI Returns the most-called tools and packs by AI agents over a 24h, 7d, or 30d window, plus total call volume.window							Reads only0.90
`pipeworx_trending` inputs `window` AI Reads only 0.90
◇ AI Reports how long each prediction-market edge has persisted and whether it is widening, stable or decaying, plus recently expired edges.days, window							Reads only0.85
`polymarket_edge_tracker` inputs `days`, `window` AI Reads only 0.85
◇ AI Returns realized win rates versus shown prices for settled short-horizon crypto up/down windows, by minute elapsed and venue.asset, bucket_pp, horizon, minute and 2 more							Reads only0.86
`prediction_calibration` inputs `asset`, `bucket_pp`, `horizon`, `minute` and 2 more AI Reads only 0.86
◇ AI Returns a previously stored value by key, or lists all saved keys when no key is given.k, key, label, name							Reads only0.90
`recall` inputs `k`, `key`, `label`, `name` AI Reads only 0.90
◇ AI Returns recent alerts from your subscription feed, optionally filtered by type or time, and can mark returned alerts as read.limit, mark_read, since, type and 1 more							Reads only0.80
`recent_alerts` inputs `limit`, `mark_read`, `since`, `type` and 1 more AI Reads only 0.80
◇ AI Returns recent SEC filings, news mentions and patent grants for a company over a chosen time window, grouped by source.since, type, value*							Reads only0.80
`recent_changes` inputs `since` (required), `type` (required), `value` (required) AI Reads only 0.80
◇ AI Lists scheduled econ, Fed, FDA and SEC releases due within a time window, with any matching live prediction markets attached.categories, hours							Reads only0.85
`release_calendar_markets` inputs `categories`, `hours` AI Reads only 0.85
◇ AI Checks whether two prediction markets settle on the same terms by diffing source, settle time, precision and evidence rules.a, b							Reads only0.80
`resolution_diff` inputs `a` (required), `b` (required) AI Reads only 0.80
◇ AI Creates a monitoring subscription that alerts you when new SEC filings, trials, or market data match your filters.delivery, params, type							Creates records0.81
`subscribe` inputs `delivery`, `params` (required), `type` (required) AI Creates records 0.81
asset, days							Reads only0.88
`updown_divergence_rate` inputs `asset`, `days` AI Reads only 0.88
◇ AI Shows the same 15-minute crypto up-or-down window priced across prediction markets, with whether each pair settles on the same contract.asset, horizon, window							Reads only0.86
`updown_venue_compare` inputs `asset`, `horizon`, `window` AI Reads only 0.86
No counted reading 26 No reading was counted, so any effect is possible.
◇ AI Assesses how visible a business, brand or topic is to one or more LLMs, returning a 0-100 score per model.context, entity*, models and 1 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`ai_visibility_check` inputs `context`, `entity` (required), `models` and 1 more
◇ AI Returns a text diff of a web page between its archived captures nearest two dates, with a similarity score and capture gaps.date_a, date_b, max_gap_days, url*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`archive_compare` inputs `date_a` (required), `date_b` (required), `max_gap_days`, `url` (required)
◇ AI Retrieves the readable text of a web page's archived capture nearest a given date, with capture time and day gap to the request.date, max_chars, max_gap_days, url	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`archive_evidence` inputs `date` (required), `max_chars`, `max_gap_days`, `url` (required)
◇ AI Returns sourced answers to factual questions about real-world data by routing each query to a matching structured data source.ask, input, message, packs and 5 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`ask_pipeworx` inputs `ask`, `input`, `message`, `packs` and 5 more
◇ AI Returns answers to a natural-language question by routing it to one of many underlying data tools.ask, input, message, packs and 5 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`ask_pipeworx_beta` inputs `ask`, `input`, `message`, `packs` and 5 more
◇ AI Returns a sourced answer to a natural-language question, quoting supporting evidence or refusing when the fetched data does not answer it.ask, input, message, prefer_tool and 5 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`ask_pipeworx_grounded` inputs `ask`, `input`, `message`, `prefer_tool` and 5 more
◇ AI Assesses which candidate labels apply to a company, using supplied text or its homepage, with a verified quote as evidence for each.entity, labels, text	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`classify_row` inputs `entity` (required), `labels` (required), `text`
◇ AI Returns the most relevant tools for a described data or task, with names, descriptions and input schemas.description, limit, q, query* and 2 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`discover_tools` inputs `description`, `limit`, `q`, `query` (required) and 2 more
domain, first_name, last_name* and 1 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`email_finder` inputs `domain` (required), `first_name` (required), `last_name` (required) and 1 more
◇ AI Verifies whether an email address is deliverable and flags disposable or webmail addresses, returning a status and confidence score.email* and 1 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`email_verifier` inputs `email` (required) and 1 more
◇ AI Summarizes a US public company's filings, financials, patents, federal contracts, hiring and news into one profile.country, type, value	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`entity_profile` inputs `country`, `type` (required), `value` (required)
max_links, url*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`generate_llms_txt` inputs `max_links`, `url` (required)
◇ AI Creates a feedback report on a bug, data gap, feature request or praise for a tool, or checks a prior report by claim token.claim_token, context, message, type	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`pipeworx_feedback` inputs `claim_token`, `context`, `message`, `type`
◇ AI Checks Polymarket prediction markets for mispriced arbitrage gaps across trending markets, one event, or a topic, net of taker fees.event, topic	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`polymarket_arbitrage` inputs `event`, `topic`
◇ AI Returns prediction-market bets where model estimates diverge from current prices, with net edge, Kelly sizing and liquidity data.category_filter, limit, max_spread_pp, min_edge_pp and 5 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`polymarket_edges` inputs `category_filter`, `limit`, `max_spread_pp`, `min_edge_pp` and 5 more
◇ AI Assesses Polymarket trades against live order-book depth, netting slippage and taker fees into realizable edge and breakeven win rates.event, market, side, size_usd	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`polymarket_fill_risk` inputs `event`, `market`, `side`, `size_usd`
kalshi_event_ticker, polymarket_event_slug, topic	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`polymarket_kalshi_spread` inputs `kalshi_event_ticker`, `polymarket_event_slug`, `topic`
◇ AI Adds a key-value memory entry for later recall; anonymous entries expire after 24 hours, while authenticated users keep them persistently.content, data, k, key* and 5 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`remember` inputs `content`, `data`, `k`, `key` (required) and 5 more
◇ AI Returns a per-company answer to a custom question, with each field backed by a verified quote from the company's website or SEC filings.entity, max_cost, output_schema, question* and 1 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`research_row` inputs `entity` (required), `max_cost`, `output_schema` (required), `question` (required) and 1 more
◇ AI Reports a prediction market's settlement clause: settling source, timing, precision, comparison basis, evidence standard, and void handling.market, venue	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`resolution_audit` inputs `market` (required), `venue` (required)
◇ AI Returns official identifiers such as ticker, CIK, LEI and FIGI for a company name or ISIN, or an RxCUI for a drug name.country, type, value	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`resolve_entity` inputs `country`, `type` (required), `value` (required)
◇ AI Reports how well AI models recognize your brand versus competitors, ranking entities by score, confidence and signal density.context, entities*, models and 1 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`scan_competitor_ai_presence` inputs `context`, `entities` (required), `models` and 1 more
◇ AI Checks an npm package's license, security advisories, release history, and bundle size before you add it to a project.package*, version	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`scan_dependency` inputs `package` (required), `version`
limit, query, text	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`search_within` inputs `limit`, `query` (required), `text` (required)
◇ AI Returns example questions grouped by category, each with the tool and arguments that answer it, optionally filtered by topic.topic	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`suggest_questions` inputs `topic`
◇ AI Verifies a factual claim and returns a verdict with cited source values; company financials are checked against SEC filings.claim*, tolerance_pct	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`validate_claim` inputs `claim` (required), `tolerance_pct`

Read as this effect No reading: unknown Not read as this effect◇ AI readings, beta. A zero is a count, not a clearance.

A2A skills 0+ observed

Inventory incomplete. The displayed count is a lower bound; missing items do not prove removal.

None recorded in this Passport.

MCP resources 0+ observed

Inventory incomplete. MCP resources could not be fully inventoried: ARD discovery did not resolve, so declarations made there were not read.

None recorded in this Passport.

MCP prompts 0+ observed

Inventory incomplete. MCP prompts could not be fully inventoried: ARD discovery did not resolve, so declarations made there were not read.

None recorded in this Passport.

OpenAPI operations 0+ observed

Inventory incomplete. OpenAPI operations could not be fully inventoried: ARD discovery did not resolve, so declarations made there were not read.

None recorded in this Passport.

The atlas shows each capability by its plain identifier, inputs and declared sign-in. Publisher descriptions, paths, links and source evidence are not published here.

The comparison with the previous observation is shown only to the account that recorded it.

Atlas history

1 observation

12 Nov 2026, 13:04 UTC47 capabilities · MCP 2025-03-26 · MCP endpoint truncated · 2 incomplete inventory groupsFirst observation
Fingerprint and versions
Fingerprint
25bf1280a85c71be239ae58d4d87dbd3e5c80a867360f1dd46ed0afd8fb5b1f4 (incomplete)
Passport schema
0.5.0, passport-semantic-v4
Consistency
MCP_PROMPTS_ADVERTISEMENT_LIST: indeterminate · MCP_RESOURCES_ADVERTISEMENT_LIST: indeterminate · MCP_TOOLS_ADVERTISEMENT_LIST: match · OPENAPI_MCP_EXPLICIT_MAPPING: not applicable

Each class compares an observation with the previous atlas observation. Runs of unchanged observations are grouped. Struck values are what the previous observation recorded; inserted values are what this one recorded.

Declared and observed

unsubscribe
Declared
The publisher declares it non-destructive.
Read
AI · beta The AI reading: deletes or cancels records (0.85).

A disagreement is not a finding about the service: either side can be wrong. How we compare declarations and readings.

About this entry

io.github.pipeworx-io/hunter
Listed
Official MCP Registry · first listed 8 Nov 2026 · last listed 8 Nov 2026

Passive observations of a public interface listed in the Official MCP Registry. An observation does not verify security, ownership or compliance, and InterfaceDelta assigns no scores or rankings. Methodology · Report an inaccuracy · Ask for removal

Identity and snapshot

Target key: sha256:08d7f48db4d0d1357f408766caca2bd7d521c969c8b92760ebeb669a0696f86d
Locator SHA-256: fcd39050134ccd4dc877323170c516ab17ecc7685d64aa664c4236643c35085b
Snapshot generated: 13 Nov 2026, 00:06 UTC

The entry is one exact observed target, not a real-world service identity, and implies no ownership. Endpoint paths are not published; the locator hash lets an operator confirm their own URL.

Capability facts

As observed from outside, at the time below

Observed: 12 Nov 2026, 13:04 UTC
Signed: 12 Nov 2026, 13:59 UTC

Protocols: MCP
Tools: 47
Declared sign-in: None declared

Effects counted AI readings, beta

Moves money: 0
Deletes or cancels records: 2
Sends messages to people: 0
Changes permissions: 0
Runs code: 0
Asks a person: 0

47 tools examined; 21 counted above a measured threshold.

Declared vs read disagreements

Declared read-only, read as writing: 0
Declared destructive, read as not writing: 0
Declared non-destructive, read as deleting: 1
Declared closed-world, read as reaching out: 0

Change since previous: First observation
Label status: Current

What an agent can do here

What changed

Look first

Surfaces

Capabilities

A2A skills 0+ observed

MCP resources 0+ observed

MCP prompts 0+ observed

OpenAPI operations 0+ observed

Atlas history

Declared and observed

Declared

About this entry