Prototype · Preview: every server in the official registry, synced every 30 minutes. Reviews and accounts come in a later step.
PopNx MCPMCP servers for people who use AI · explained in plain words
☰ MenuEnglish Settings
Beginner mode On
ColoursSystemLightDark
LanguageไทยEnglish中文日本語한국어EspañolDeutsch

KnownFix

by b-hash88version 0.6.1i★ 1iComputer or cloud
Registry nameio.github.b-hash88/knownfix

Install

Overview

Description from the maker (original English)

Developer fixes, free skills, browser tools and scoped technical services over MCP.

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

Install

Pick the AI app you use, then copy the settings.

Before you install

You need

Which app do you use?

Pick your app above. We remember it, so next time the button says “Install in …”.

Works in Claude on the web, desktop and mobile:

  1. Open Settings → Connectors
  2. Press Add custom connector
  3. Paste the address below and press Add
  4. If it asks you to sign in, sign in with the maker
SettingsConnectors1+ Add2https://…3Connect4
https://knownfix-backend-28.b-hash88.deno.net/mcp

Or run it on your computer

Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json

{
  "mcpServers": {
    "knownfix": {
      "command": "npx",
      "args": [
        "-y",
        "knownfix",
        "bridge"
      ]
    }
  }
}

Run this in your terminal

claude mcp add --transport http knownfix https://knownfix-backend-28.b-hash88.deno.net/mcp

Or run it on your computer

claude mcp add knownfix -- npx -y knownfix bridge

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "knownfix": {
      "url": "https://knownfix-backend-28.b-hash88.deno.net/mcp"
    }
  }
}

Or run it on your computer

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "knownfix": {
      "command": "npx",
      "args": [
        "-y",
        "knownfix",
        "bridge"
      ]
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "knownfix": {
      "type": "http",
      "url": "https://knownfix-backend-28.b-hash88.deno.net/mcp"
    }
  }
}

Or run it on your computer

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "knownfix": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "knownfix",
        "bridge"
      ]
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

ChatGPT connects only to servers on the internet:

  1. Open ChatGPT on the web → Settings → Connectors (Apps)
  2. Press Create or Add (some plans need Developer mode under Advanced first)
  3. Paste the address below, give it a name and save
  4. If it asks you to sign in, sign in with the maker
SettingsConnectors1+ Create2https://…3Connect4
https://knownfix-backend-28.b-hash88.deno.net/mcp

Menu names can differ slightly by plan and over time.

Your choice stays on this device in a cookie; no account needed.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

Which apps can use it

Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.

Connect over the internet in

ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast

Run on your computer in

ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast

All apps, with pros and cons →

Related guides

Guide 85 checks before you install an MCPAbout 2 minutes each: check its page on our site and the permission request in your AI app before you say yes.4 min read

What it can do

Tool names and descriptions exactly as the server reported them on Nov 7, 2026. The maker wrote them, not us; we show them as plain text.

  • get_free_skill

    Return the complete Markdown body of one free workflow listed by get_overview. No account, payment, paid body or private data. Use list_skills/get_skill for premium products instead. This tool supports clients that cannot read MCP resources.

  • get_overview

    One free overview of all KnownFix offerings: complete free-workflow resource URIs, three browser-local tools and their companion guides, catalog routes, premium outlines and service prices/scopes/ordering boundaries. No account, payment, signed offer or order creation. Use search

  • search_fixes

    Use this first for an exact error or distinctive symptom. Returns up to three confident ranked matches. A free top match includes the full fix. A paid top match includes a free diagnosis, confidence and compatibility, dollar price, signed USDC/Base Pay and exact-ETH rails, and on

  • request_fix

    Ask for a fix this store does not have yet. If we already stock it (matched on either field) you get the id straight back and no ticket. Otherwise you get a ticket; when we stock THAT fix, check_request returns it to you FREE, once. A ticket only ever redeems a fix created after

  • check_request

    Check a private ticket from request_fix. Returns pending, declined, not-eligible, redeemed, or the full fix free once an eligible new fix is stocked. This call may atomically consume the ticket's one-time delivery, so save the returned body. Use get_fix when you already have a ca

  • list_catalog

    Browse every stocked error signature, title, tag, confidence label, and free-sample flag without ranking or creating an offer. Use search_fixes instead when diagnosing a specific error; it returns the best match and any purchase-ready checkout.

  • list_skills

    Compare premium skills and multi-fix bundles. Returns current ids, free outlines, provenance, formats, and exact prices while full bodies remain paid. Call get_skill with a chosen id for signed USDC and ETH checkout; use search_fixes for a single error.

  • list_merch

    Browse the KnownFix Merch Store. Returns fixed product ids, lines, formats, and privacy-safe tracked links to the human Fourthwall storefront. Fourthwall shows the current localized price, options, tax, shipping, and availability. This tool does not place an order or collect chec

  • list_services

    Compare all current KnownFix reviews, Verified Repo Fix and Microsite Launch. Returns complete scope, deliverables, prices, delivery targets and limitations. Services requiring scope approval or payment after verified delivery are manual: use their order page, not order_service.

  • order_service

    Create a private ticket and signed Base USDC/ETH checkout for an eligible automated service only. Do not call for requiresScopeApproval services (SaaS security, Microsite Launch) or paymentTiming:after-verified-delivery (Verified Repo Fix); these require manual scope approval via

  • check_service_order

    Check a private service order by its svc_ ticket. With paymentTx and paymentOffer, atomically confirms exactly one matching Base payment and moves the order into review. Without payment fields, returns current status; once complete, it returns the private Markdown report and SHA-

  • audit_endpoint Looks like an instruction to the AI

    Readiness audit of any agent-facing URL: MCP handshake, CORS, discovery docs (llms.txt, mcp.json), and payment-offer behaviour. First call with url alone for the FREE grade and failing-check list. For the full findings and remediations, call get_offer with productType "audit" and

  • audit_theme

    Run a read-only theme audit on a public HTTP(S) page, free in full. Fetches but never modifies the page, then checks inline style CSS for brace errors, token gaps, incomplete dark themes, missing body backgrounds, and WCAG body-text contrast. External stylesheets are counted but

  • get_offer

    Create or refresh a one-hour signed bearer offer for a chosen skill, bundle, audit, or fix. Do not call this after a paid search_fixes result or an unpaid get_fix/get_skill result because those responses already include both payment rails. Choose USDC for Base Pay or ETH for exac

  • report_checkout_blocker

    Use only after a signed KnownFix checkout cannot proceed before a payment hash exists. Reports one closed-vocabulary blocker tied to the valid offer; at most one aggregate count is accepted per offer. No wallet address, token, transaction hash, query, or free-form text is publish

  • get_fix

    Get or redeem a fix after search_fixes or list_catalog identifies the id. Free samples return immediately. For a paid fix, call with the id alone to receive a free diagnosis preview, confidence and compatibility, dollar price, signed Base Pay USDC and exact-ETH offers, and one pa

  • get_skill

    Get or redeem a premium skill or multi-fix bundle after choosing with list_skills. Call with the id alone to receive the free outline, dollar price, signed Base Pay USDC and exact-ETH offers, and one pay-and-redeem action. After payment, call once more with the matching paymentTx

  • submit_fix

    Offer a fix for the catalog. Submissions are reviewed by the operator before listing; include a reproduction so the fix can be verified rather than trusted. Returns a private submissionId; save it and call check_submission for pending, accepted, declined, or cataloged status. Sub

  • check_submission

    Check the private submissionId returned by submit_fix. Returns only pending-review, accepted, declined, or cataloged state and, when cataloged, the stocked fix id. It never returns submitted text or contributor details and creates no side effects. Use get_fix with catalogId when

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 11, 2026

  • ✓ Pass

    Maker matches the repo

    The registry name was verified with the GitHub account b-hash88, which owns the repo

  • ✓ Pass

    Still maintained

    Code last changed 22 days ago

  • … Not checked yet

    Has a licence

    We have not read this repo from GitHub yet

  • ✓ Pass

    Endpoint responds

    Responded in 791 ms (HTTP 200)

  • – Not applicable

    Sign-in with OAuth

    No sign-in needed

  • ✕ Fail

    No hidden instructions in tool descriptions

    1 tool descriptions contain text that looks like instructions to the AI. Read them below before installing

Compared with others in Web & browsersi

  • More stars than 75% of the other 1448 servers in this category
  • Published to the registry more recently than 58% of the other 1448 servers in this category
  • Basic checks equal to or better than 50% of the other 1448 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is KnownFix safe?

It passed 3 of 4 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

The registry does not list a required key, though some servers ask you to sign in on first use.

Does it run on my computer or in the cloud?

Either way works: install it on your computer or connect to the cloud version.

Is it still maintained?

The GitHub repo last changed 22 days ago, and the latest version (0.6.1) reached the registry 22 days ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.

What can I use instead?

In the same category: Browser Use, Scrapling MCP Server, Chrome DevTools MCP

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Browser Use

Lets AI do web tasks for you, such as filling forms, searching and extracting data, in the maker’s cloud browsers or on your computer.

by browser-useWidely used↓ 1.7M/wk★ 120.5KUpdated 21 days ago

Computer or cloud✓ browser-use.com
Install

Scrapling MCP Server

Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported.

by D4VinciWidely used↓ 396.9K/wk★ 100.8KUpdated 6 days ago

Runs on your computer
Install

Chrome DevTools MCP

Lets AI use Chrome’s developer tools to inspect pages, find what makes them slow and spot errors. Made by the Chrome DevTools team.

by ChromeDevToolsWidely used↓ 1.9M/wk★ 55KUpdated 19 days ago

Runs on your computer
Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

KnownFix

KnownFix is an agent-facing catalog of development-error fixes. The current overview reports inventory and evidence labels; fourteen fixes are available in full for free. Search is free; paid fixes start at $0.05 USDC through Base Pay or a signed exact-ETH equivalent on Base mainnet.

KnownFix offers ten scoped services, including website audits, a homepage build, code and release reviews, a Webhook Reliability Review ($179 USDC / 3 business days), and a SaaS Security Exposure Review ($299 USDC / 5 business days). Verified Repo Fix is $149 USDC / 3 business days from scope acceptance and a complete reproducible brief, with payment only on verified delivery. Microsite Launch is $299 USDC / 5 business days after scope approval, approved content/assets and manual payment before work. SaaS security requires written ownership/testing permission and an agreed target/method/window allowlist before payment or testing; its five-day target begins after approval, payment and required access. These three services use manual scope/payment arrangements, not automated checkout. Other review targets begin after payment and a complete in-scope brief. The service catalog is authoritative.

Three free browser-local tools complement six free workflow skills: MCP Connection Kit, MCP Response Inspector, and Webhook Retry Planner. The planner compares capped backoff and full-jitter timing against a time budget. It sends no webhooks and saves no settings. Optional analytics records fixed action labels only; those events are not unique users or successful deliveries.

Storefront Checks

Website analytics uses GA4 G-PPPE9TYRM2 (property 559407250). The earlier G-781DC76YQN is the Fourthwall shop stream, not the website reporting source. Never merge shop visits or MCP request counters into website visitor totals. The website property reports in America/Vancouver; a UTC test can fall on the previous reporting day. Consent is opt-in, advertising stays denied, and QA events are not customer activity. Report processing is separate from transport.

tests/analytics-property.mjs checks every HTML page and marked action, failing on missing tracking rather than silently skipping new pages. Four deliberate exclusions stay untracked: the ownership-verification file, fictional Patchnote demo and two sample reports. tests/analytics-consent-lifecycle.mjs covers every tracked wrapper. tests/analytics-coverage-browser.mjs loads all tracked pages and exercises homepage actions with Google and backend writes blocked; it uses the installed-Playwright recipe below. tests/tool-guides-browser.mjs verifies the three tools' check, copy, download, calculate, reset and guide actions. The opt-in tests/tool-guides-live-analytics.mjs creates synthetic QA events in temporary profiles only. HTTP204 is transport evidence, not proof of GA4 report receipt; verify the matching main-site property separately. Never alter an owner's saved consent or use a live checkout to test analytics.

Three companion guides live under guides/, with nine fixed synthetic JSON examples, linked from the tools, homepage and free-skills hub. Regenerate this content with node scripts/sync-tool-guides.mjs. The MCP-kit and retry-planner generators also run this sync. node tests/tool-guides.mjs checks reproducible outcomes, links, downloads, analytics boundaries and generator idempotence. tests/tool-guides-browser.mjs uses the same installed-Playwright environment recipe below; KNOWNFIX_BROWSER_CHANNEL=msedge selects an installed Edge. Guide events use guide_action with fixed open-tool, download-example and related-guide contexts. Tool examples reuse the respective tool action event; no pasted input or entered settings enter these events. All require consent.

Run node tests/retry-planner.mjs and node tests/service-comparison.mjs for the new tool and catalog consistency. The existing Gitea workflow includes both. tests/retry-planner-browser.mjs uses the existing KNOWNFIX_PLAYWRIGHT_PATH recipe to resolve an installed Playwright package without downloading one. Set PLAYWRIGHT_BROWSERS_PATH to the installed browser cache when needed and KNOWNFIX_SCREENSHOT_DIR to retain desktop/mobile screenshots. Tests start and close a temporary localhost server and block real backend writes.

Regenerate the planner with node scripts/sync-retry-planner.mjs, then run node scripts/sync-site-improvements.mjs to refresh catalog comparison and links. The service sync also refreshes that comparison after catalog changes.

Connect an agent

Use the client-specific connection kit for Claude Code, Codex, Cursor, VS Code or the Claude Desktop stdio bridge. It includes supported install links and a free first-use example. Configuration, tool discovery and successful workflow retrieval are distinct milestones.

Install the free toolkit

Six standard skills/ /SKILL.md directories contain the complete free workflows, synthetic exercises and acceptance criteria. Review them, then use npx skills add b-hash88/knownfix to choose a client and scope interactively, or copy reviewed directories using the client's documented skill installation.

The toolkit also provides dependency-free local commands:

node toolkit/cli.mjs inspect-response toolkit/examples/response.json

node toolkit/cli.mjs retry-plan toolkit/examples/retry.json

Node.js 18+, file/stdin JSON, 200,000-byte cap. No network or telemetry during these commands. Envelope structure is not tool success; modeled retries do not send webhooks. Run node scripts/sync-agent-toolkit.mjs after changing skill or browser-core sources, and node tests/agent-toolkit.mjs to verify parity.

Remote endpoint

KnownFix is listed as io.github.b-hash88/knownfix. Its remote Streamable HTTP MCP endpoint is:

https://knownfix-backend-28.b-hash88.deno.net/mcp

The live registry exposes search, catalog, signed offers, fix and skill delivery, endpoint audits, submissions, fix requests, professional review ordering and retrieval, and a read-only apparel catalog through list_merch. npx knownfix tools prints the current list instead of relying on copied docs. The branded Smithery directory name is knownfix/knownfix.

For the current npm Trusted Publishing failure, search the exact CLI signature:

npx knownfix search "npm ERR! code EOTP"

KnownFix also matches This operation requires a one-time password from your authenticator. and the npm --otp= wording. The public diagnostic page cites npm's current CLI source; the npm Publishing Recovery Pack contains the six-fix decision tree and verification commands.

Paid delivery

Free fixes return immediately. A paid search_fixes match includes a free diagnosis preview, confidence and compatibility, dollar price, a private signed offer, wallet/payment URI, and one recommended next action. Each one-hour offer is bound to one product, one currency, and one payment intent:

  1. Use the offer returned by search_fixes, or request one directly with MCP get_offer or POST /offer.
  2. Keep the bearer token private. Use the exact Base Pay parameters for USDC or pay exactly priceWei for ETH on chain 8453.
  3. Redeem with paymentTx plus paymentOffer, or the corresponding HTTP headers. For USDC, paymentTx is the returned ERC-4337 UserOperation hash; for ETH, it is the mined transaction hash.

The payment proof and offer are atomically single-use in Deno KV. A public chain hash alone is not accepted as a purchase credential. The store also carries five crawlable recovery packs for npm, GitHub Actions, MCP, Windows agent shells, and Base payment verification.

Honesty contract

verified-in-production means reproduced and fixed in a real session; documented means sourced but not independently reproduced. An unmatched search returns empty. The books distinguish raw requests, MCP polling, real tool calls, deliveries, paid intent, and settled sales.

KnownFix is AI-operated on human-owned hosting, deployment, and treasury infrastructure. No buyer account or API key is required.

Live end-to-end test

Run the dependency-free production suite with Node 20 or newer:

node tests/live-e2e.mjs

The suite crawls every canonical URL and checks the current free/paid page pairs, product packs and service catalog, HTTP and MCP search/delivery/offer flows, distinct UserOperation and transaction proofs, anonymous stats access controls, and security headers. Requests carry x-operator: 1 so delivery and purchase-intent tests do not contaminate those conversion counters. Set KNOWNFIX_SERVICE_ORDER_TARGET to an authorized public URL only when intentionally testing creation of one private operator order; routine runs do not fill the order queue.

Public Discovery And Site Quality

agents.html is the human-readable MCP start page; notes-for-agents.md is its portable counterpart. Start with get_overview / knownfix://overview / backend GET /overview. get_free_skill({id}) supports tool-only clients; resource-capable clients can read each knownfix://free-skill/ directly. There are three local browser tools, three guides, six full free workflows, eleven premium workflow outlines and ten scoped services. Manual approval and payment-on-delivery services never use upfront automated orders.

After other storefront generators, run node scripts/sync-site-quality.mjs. The guide and comparison generators invoke this finalizer too. It preserves prices/scopes, aligns payment metadata, maintains fix landmarks/navigation, and applies current-consent/own-property analytics guards. premium-skills.json contains only allowlisted fields from the public backend /skills response, not paid bodies. Refresh that snapshot only after checking current public terms. node tests/site-quality.mjs protects consistency and generator idempotence. scripts/audit-site.mjs uses the same explicitly configured installed Playwright runtime as the browser suites to inspect all public HTML and local links.