Name: Web Fetch
Author: pipeworx-io

Web Fetch MCP

web-fetch — fetch ONE public URL live from its origin, verbatim.

Grade A Remote or local · Streamable HTTP · stdio No auth needed 15 tools v0.2.1 · 6 Nov 2026 MIT

No reviews yet by pipeworx-ionpm 545 Runs on your machine or at its publisher’s address — not through us

100/100

trust score

downloads a day

local

or remote

545

downloads in 30d

What it does

web-fetch — fetch ONE public URL live from its origin, verbatim.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user pipeworx-io-web-fetch-mcp '--' npx -y @pipeworx/mcp-web-fetch

# 2 — ask your agent for something these tools do
#   fetch_url, ask_pipeworx, ask_pipeworx_beta and 12 more

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

Publishernot claimed

pipeworx-io1913 servers

29 categories

All 1913 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. This one can run either way — at an address its publisher runs, or as a process under your own user, with your files and your network — and this marketplace is in the path of neither.

Claude Codedeclared by this listing

This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.

claude mcp add --scope user pipeworx-io-web-fetch-mcp '--' npx -y @pipeworx/mcp-web-fetch

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

Or connect to its publisher’s address

Its publisher also runs it at https://gateway.pipeworx.io/web-fetch/mcp: nothing to start on your machine, and this marketplace is not in the path.

claude mcp add --scope user --transport http pipeworx-io-web-fetch-mcp https://gateway.pipeworx.io/web-fetch/mcp

Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.

What it asks of you

Nothing is required, but it can take PIPEWORX_API_KEY (Optional Pipeworx API key. Without it calls are anonymous and capped daily; a free key raises the cap.) if you want to set it.

What it writes

One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.

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.

Only tools that write or reach the network

Fetch the exact contents of ONE public web URL live from its origin server and return them verbatim with a SHA-256 hash of the bytes received. Use it to read a specific page, raw data file (CSV, TSV, .dat, JSON, XML), API endpoint or PDF whose address you already know. format "auto" (default) returns readable text for HTML and PDF and the raw body for everything else; "raw" returns the body itself

Parameter	Type	Required	Notes
url	string	yes	The absolute http(s) URL to fetch, e.g. "https://data.giss.nasa.gov/gistemp/tabledata_v4/GLB.Ts+dSST.csv". http:// is tried over https first.
format	string	no	auto (default): text for HTML and PDF, raw for everything else. raw: the body as received. text: readable text extracted from HTML/PDF.
max_bytes	number	no	Size of the returned window. Default 100000. Maximum 1000000 for text, 512000 for base64 (binary).
offset	number	no	Where the window starts: a byte offset into the body (raw), or a character offset into the extracted text (text). Use next_offset from the previous call to page. Default 0.

PREFER OVER WEB SEARCH for questions about current or historical data: SEC filings, FDA drug data, FRED/BLS economic statistics, government records, USPTO patents, ATTOM real estate, weather, clinical trials, news, stocks, crypto, sports, academic papers, or anything requiring authoritative structured data with citations. Routes the question to the right one of 7,121 tools across 1849 verified sou

Parameter	Type	Required	Notes
question	string	yes	Your question or request in natural language. Accepts query, q, prompt, text, input, ask, message as aliases.
query	string	no	Alias for question.
q	string	no	Alias for question.
prompt	string	no	Alias for question.
text	string	no	Alias for question.
input	string	no	Alias for question.
ask	string	no	Alias for question.
message	string	no	Alias for question.
packs	array	no	OPTIONAL. Restrict routing to these pack slugs (e.g. ["sec-form-d","sec-13f"]) — the router then picks only from tools in those packs. Omit for the default full-catalog routing. Slugs come from list_p

Beta version of ask_pipeworx: identical universal router (same 7,121 tools, same arguments, same response shape) with candidate routing improvements enabled live whenever one is under test. No candidate is active right now (the last was retired on outcome evidence 2026-07-26), so this currently matches ask_pipeworx exactly. Use it exactly like ask_pipeworx when you want the newest routing; results

Parameter	Type	Required	Notes
question	string	yes	Your question or request in natural language. Accepts query, q, prompt, text, input, ask, message as aliases.
query	string	no	Alias for question.
q	string	no	Alias for question.
prompt	string	no	Alias for question.
text	string	no	Alias for question.
input	string	no	Alias for question.
ask	string	no	Alias for question.
message	string	no	Alias for question.
packs	array	no	OPTIONAL. Restrict routing to these pack slugs (e.g. ["sec-form-d","sec-13f"]) — the router then picks only from tools in those packs. Omit for the default full-catalog routing. Slugs come from list_p

Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 7,121 across 1849 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_

Parameter	Type	Required	Notes
question	string	yes	Your question in natural language. Accepts query, q, prompt, text, input, ask, message as aliases.
query	string	no	Alias for question.
q	string	no	Alias for question.
prompt	string	no	Alias for question.
text	string	no	Alias for question.
input	string	no	Alias for question.
ask	string	no	Alias for question.
message	string	no	Alias for question.
prefer_tool	string	no	Run this exact tool instead of letting the router choose — use a name from a previous answer's alternatives[]. Arguments are still filled from your question. Unknown names are refused, never guessed.

ACCOUNT REQUIRED (free — sign in via GitHub at https://pipeworx.io/signup; depth:"thorough" needs a paid plan). If you are not signed in, use ask_pipeworx instead — it works on every tier. Grounded multi-source research across Pipeworx's 1849 STRUCTURED data sources (SEC filings, FRED/BLS economics, FDA, USPTO patents, markets, science, government records, etc.) in ONE call — this is NOT open-web

Parameter	Type	Required	Notes
question	string	yes	The research question, in natural language. Broad/multi-part is fine — decomposition is the point. Accepts query, q, prompt, text, input, ask, message as aliases.
query	string	no	Alias for question.
q	string	no	Alias for question.
prompt	string	no	Alias for question.
text	string	no	Alias for question.
input	string	no	Alias for question.
ask	string	no	Alias for question.
message	string	no	Alias for question.
depth	string	no	How many facets to research in parallel: quick=3 (single hop), standard=3 (default; adds a gap-recovery hop that re-angles unanswered facets + a contradictions[] scan across findings), thorough=6 (pai

Pull fired events from your subscription feed. Returns the most recent alerts the evaluator has written to your persisted feed — each carries source, citation_uri (pipeworx:// when available), and the raw event payload. Filter by type (e.g. "sec_8k") and/or since (ISO timestamp). Set mark_read:true to flag returned events read so the next call only shows newer ones. Polls work fine; the same feed

Parameter	Type	Required	Notes
type	string	no	Optional — filter to one subscription type.
since	string	no	Optional ISO timestamp — return events fired_at >= this time.
limit	number	no	Max events to return (1-200, default 50).
unread_only	boolean	no	Return only events where read_at is null (default false).
mark_read	boolean	no	Flag the returned events read in the same call (default false).

TYPED, DETERMINISTIC financial facts for a US public company for an EXPLICITLY NAMED reporting period — "Apple revenue for fiscal 2023", "Walmart net income FY2026 Q3", "Microsoft cash at the end of fiscal 2024". PREFER OVER entity_profile / get_company_financials whenever the period matters: those answer "the most recent figures" and will happily hand back FY2025 when you asked about FY2019, and

Parameter	Type	Required	Notes
company	string	yes	Ticker ("AAPL"), 10-digit CIK ("0000320193"), or company name. A name that matches two filers equally well returns status "ambiguous" with both named rather than guessing — pass a ticker or CIK to be
attribute	string	yes	Which figure. "revenue" = total consolidated revenue; "net_income" = net income (loss); "cash" = cash and cash equivalents at the period end; "gross_profit"; "operating_income"; "eps_diluted" (diluted
period	object	yes	The reporting period, stated explicitly. There is no default and no "latest" — that is the point of this tool.
freshness	string	no	cached (default) permits an eligible stored answer; fresh requires an upstream refresh and never silently falls back to stale data.
max_age	number	no	Maximum age in seconds of the upstream publication, not our fetch. Older or undated facts are withheld.
as_of	string	no	Past ISO timestamp with timezone. Replay the latest answer actually recorded by that instant; no invented history or live fallback.
restatement	string	no	Default "as_amended" — the latest filed figure for the period, with everything it superseded listed. "as_originally_reported" takes the first filing instead.
basis	string	no	Only "consolidated" in v1. Segment and product-level figures are XBRL-dimensioned and are not reachable through this contract at any concept.
exclude_publishers	array	no	Publisher ids forbidden for fact retrieval: sec, fmp, alphavantage. Case and surrounding whitespace are normalized; unknown ids are refused. Excluding sec currently leaves no eligible fact source and

Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call. Pass a market slug ("will-kristi-noem-win-the-2028-republican-presidential-nomination"), a polymarket.com URL, or a question text. Prefer an UNDATED slug: a dated one ("...-by-june-30-2026") stops resolving the day it settles, because Polymarket de-indexes resolved markets. The tool resolves the market, classifies

Parameter	Type	Required	Notes
market	string	yes	Polymarket slug ("will-kristi-noem-win-the-2028-republican-presidential-nomination"), full URL ("https://polymarket.com/event/..."), or question text ("Will Bitcoin hit $150k?"). Dated slugs stop reso
depth	string	no	quick = 2-3 evidence sources, thorough = full fan-out. Default thorough.
include_raw	boolean	no	Default false. When false (recommended), FRED/FDA/GDELT/Federal-Register evidence is summarized to the few fields agents actually use — keeps responses under ~20KB. Pass true to get full upstream payl

Edge persistence and decay telemetry built from daily polymarket_edges snapshots. Answers "how long has this edge existed and is it shrinking?" — a fresh wide edge and a 3-week-old wide edge are different trades (the latter is wide for a reason nobody is willing to take). Args: days (lookback, default 14, max 30), window (snapshot family, default "1wk"). RESPONSE: tracked[] = every opportunity in

Parameter	Type	Required	Notes
days	number	no	Lookback in days (default 14, clamp 2-30).
window	string	no	Which polymarket_edges window family to read snapshots for: 24hr \| 1wk \| 1mo (default 1wk).

JOIN of the official release calendar (econ data, the FOMC, FDA decisions, SEC rules) against LIVE Polymarket/Kalshi markets — which scheduled releases land in the next N hours, and which live markets resolve on them. This is a POSITIONING tool, not a speed product: results are cached like every other pack (≤ 60s TTL) and there is no push/webhook — do not use this to try to beat a release, use it

Parameter	Type	Required	Notes
hours	number	no	Look-ahead window in hours from now. Default 48. Capped at 720 (30 days) — econ/fed releases are dated weeks apart, so a short window is often empty; widen rather than assume nothing is scheduled.
categories	string	no	Comma or space separated subset of econ\|fed\|fda\|sec\|court, or "all" (default). E.g. "econ,fed" or "fda".

The same 15-minute crypto "up or down" window priced on polymarket.com, Polymarket US and Kalshi, side by side, with whether each pair is actually the same contract. Pass asset (btc | eth | sol | xrp | bnb) and window ("current" default, "next", "previous", or the window START as ISO such as 2026-10-27T14:15:00Z, on a 15-minute boundary). Per venue: question, Up bid / ask / mid / last, spread_pp,

Parameter	Type	Required	Notes
asset	string	no	btc (default) \| eth \| sol \| xrp \| bnb. Coverage differs by venue; a venue that does not list the asset answers not_listed.
horizon	string	no	15m (default and the only value offered).
window	string	no	"current" (default), "next", "previous", or the window START as an ISO-8601 timestamp on a 15-minute boundary, e.g. 2026-10-27T14:15:00Z. An unaligned timestamp is refused, not rounded.

How often two venues settled the SAME 15-minute crypto window differently, over every settled window on record. Compares polymarket.com (Chainlink TWAP) with Kalshi and with Polymarket US (both CF Benchmarks BRTI), and Kalshi with Polymarket US as the same-feed control. Per pair: windows both venues settled, divergent count, the rate with its 95% Wilson interval (withheld under 30 paired windows),

Parameter	Type	Required	Notes
asset	string	no	btc (default) \| eth \| sol \| xrp \| bnb. The archive holds btc/eth on all three venues, sol/xrp on polymarket.com and Polymarket US, bnb on Kalshi only (no pair).
days	number	no	Look-back in days, 1-90 (default 30). The archive starts 2026-09-22 (polymarket.com, Kalshi) and 2026-10-07 (Polymarket US, btc), so a longer span is capped by what is held; coverage is reported per p

What changed on a web page between two dates? Resolves the archived capture nearest each date (Internet Archive Wayback Machine, Common Crawl, Arquivo.pt), extracts the readable text of both, and returns a text-level diff: the segments removed and added, a similarity score, and both capture timestamps with their gaps from the requested dates. It diffs readable text, not markup, so a restyled page

Parameter	Type	Required	Notes
url	string	yes	The page address, e.g. "https://www.ftc.gov/policy-notices/privacy-policy".
date_a	string	yes	The earlier date, as YYYY-MM-DD (e.g. "2021-06-01").
date_b	string	yes	The later date, as YYYY-MM-DD (e.g. "2024-06-01").
max_gap_days	number	no	Furthest a capture may be from each date and still be used, in days. Default 30, max 3650.

Tell the Pipeworx team something is broken, missing, or needs to exist. Use when a tool returns wrong/stale data (bug), when a tool you wish existed isn't in the catalog (feature/data_gap), or when something worked surprisingly well (praise). ONLY for tools served by this Pipeworx connection — if the tool came from a different MCP server in your client (another vendor's Gmail, Splunk, Slack, etc.

Parameter	Type	Required	Notes
type	string	no	bug = something broke or returned wrong data. feature = a new tool or capability you wish existed. data_gap = data Pipeworx does not currently expose. praise = positive note. other = anything else.
message	string	no	Your feedback in plain text. Be specific (which tool, what error, what data was missing). 1-2 sentences typical, 2000 chars max.
context	object	no	Optional structured context: which tool, pack, or vertical this relates to.
claim_token	string	no	Read the reply to a report you filed earlier: pass the pwfb_… token that filing returned, with no other arguments. Returns the status and, once resolved, what actually changed.

Save data the agent will need to reuse later — across this conversation or across sessions. Use when you discover something worth carrying forward (a resolved ticker, a target address, a user preference, a research subject) so you don't have to look it up again. Stored as a key-value pair scoped by your identifier. Authenticated users get persistent memory; anonymous sessions retain memory for 24

Parameter	Type	Required	Notes
key	string	yes	Memory key (e.g., "subject_property", "target_ticker", "user_preference"). Accepts name, k, label as aliases.
value	string	yes	Value to store (any text — findings, addresses, preferences, notes). Accepts content, text, data, v as aliases; a non-string value is stored as JSON.
name	string	no	Alias for key.
k	string	no	Alias for key.
label	string	no	Alias for key.
content	string	no	Alias for value.
text	string	no	Alias for value.
data	string	no	Alias for value.
v	string	no	Alias for value.

Free

$0 forever

Every tool, no call limit
No card, and mcprush charges nothing for it
Source published under MIT
Runs on your machine — nothing of it reaches our gateway
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install Web Fetch or to call it, at any volume.

ATrust score 100 / 100

Release 0.2.1 · scanned 6 Nov 2026

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 score100

Findings0 threat · 0 capability

Capabilityminimal

Coveragesource

Verificationsource

Surface digest2b28906d656239c5ed964da57b143d56837f0a929ff6cf00f6cbd4eb3b430f7a

Score vectorthreat 100 → client 100

Term	Level	What it prices	Points
capability-exposure	minimal	capability blast radius (minimal) — client exposure if the model is manipulated	−0
verification-discount	source	publisher verification (provenance) — cryptographic build provenance ties the artifact to its source	−0
coverage-honesty	source	inspection depth (source) — how much of the target the scan could see	−0

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.

Tool surfacenot available

Implementation sourceread

Package metadataread

Live transportnot available

No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".

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
No per-tool rows for this release — see the note below.

No tool surface was enumerated, so there is nothing to attribute a capability to.

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 digest2b28906d656239c5

Scanned2026-11-06

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.