Skip to main content
Glama
605,063 tools. Updated 2026-09-23 22:39

"Axios" matching MCP tools:

  • Post-process a RAW generated mesh (normalize → mesh-repair → rig/skin → validate → export) and return the finished, validated GLB as base64. The inline counterpart of axis_process (which needs a server file path) — the generation post-process step, callable by an LLM/agent that holds the mesh bytes (e.g. fresh TRELLIS output) or a URL to them. Provide the mesh EXACTLY one of two ways: inline as base64 (glb_base64) or as an HTTPS URL (mesh_url) — the URL's host must be on this server's operator-configured allowlist (off by default; an unconfigured allowlist refuses every mesh_url call, it is never open to an arbitrary host). Providing both or neither is a real input error. [Paid: $1.50 USDC via x402 for unauthenticated calls on the hosted /mcp endpoint; settled only on a successful (non-error) result.]
    ConnectorNo auth
  • POPLA's own record of how private parking appeals were decided, per operator, across its 2023, 2024 and 2025 annual reports. Give an operator for its three-year series and its change in percentage points; omit it for the all-operator totals and a ranking. These are decided appeals only — appeals an operator withdraws end in the driver's favour without a ruling and are counted separately.
    ConnectorNo auth
  • Write WHOLE files DIRECTLY — YOUR model generates the code, Kleap stores, builds and deploys it as-is. To change something in a file that ALREADY EXISTS, use edit_files instead (read_files → edit_files): it replaces just the lines you name, while write_files makes you retype the entire file and silently drops whatever you leave out — on a 30KB shared layout that is how headers and footers get wiped. No Kleap-AI step, so what ships is byte-for-byte what you wrote — the right choice when a phrase, a URL or a schema must be exact. Publishing still audits the result (see publish_app). Best for scaffolding exact pages/components — e.g. programmatic-SEO routes. Astro paths (src/pages/*.astro, src/data/*.json, src/components/*.astro, public/*). Overwrites by path. NPM PACKAGES: do not write package.json (the build replaces it) — the build installs whatever your code IMPORTS, so `import { jsPDF } from "jspdf";` is all it takes. Supported on import: @tiptap/*, jspdf, pdf-lib, html2canvas, papaparse, file-saver, jszip, @ffmpeg/*, howler, wavesurfer.js, browser-image-compression, react-dropzone, recharts, chart.js, d3, @tanstack/*, react-hook-form, three, @react-three/*, leaflet, maplibre-gl, gsap, framer-motion, zustand, date-fns, react-markdown, axios, socket.io-client, radix-ui/*, next-themes, lucide-react, @tabler/*, openai, @ai-sdk/*; anything else is refused at build with a message naming it. A client-side router is never the answer — a route is a FILE (src/pages/about.astro → /about). IMAGES AND BINARIES: set encoding:"base64" on the file and send the bytes — that is how you put a logo, a photo, an OG image, a favicon or a font on the site (png/jpg/webp/svg/ico/mp4/woff2/pdf, 512KB max each decoded). Without it you can only write text, and a site with no images looks unfinished. To ADD an image from a text prompt WITHOUT sending any bytes (a real photo's base64 is too big to emit reliably), use generate_image — Kleap generates it and stores it for you. To REMOVE a page or asset, use delete_files — overwriting it with empty content leaves a URL that answers 200 with nothing, which is worse than a 404. DATA & ACCOUNTS: write_files only STORES files — it cannot provision the Kleap Database, so DB or auth code pushed here has no backend and silently does nothing. Stand the feature up with modify_app first, then edit those pages here. After writing, call publish_app to build & go live.
    Connector
    Destructive
    OAuth
  • Write WHOLE files DIRECTLY — YOUR model generates the code, Kleap stores, builds and deploys it as-is. To change something in a file that ALREADY EXISTS, use edit_files instead (read_files → edit_files): it replaces just the lines you name, while write_files makes you retype the entire file and silently drops whatever you leave out — on a 30KB shared layout that is how headers and footers get wiped. No Kleap-AI step, so what ships is byte-for-byte what you wrote — the right choice when a phrase, a URL or a schema must be exact. Publishing still audits the result (see publish_app). Best for scaffolding exact pages/components — e.g. programmatic-SEO routes. Astro paths (src/pages/*.astro, src/data/*.json, src/components/*.astro, public/*). Overwrites by path. NPM PACKAGES: do not write package.json (the build replaces it) — the build installs whatever your code IMPORTS, so `import { jsPDF } from "jspdf";` is all it takes. Supported on import: @tiptap/*, jspdf, pdf-lib, html2canvas, papaparse, file-saver, jszip, @ffmpeg/*, howler, wavesurfer.js, browser-image-compression, react-dropzone, recharts, chart.js, d3, @tanstack/*, react-hook-form, three, @react-three/*, leaflet, maplibre-gl, gsap, framer-motion, zustand, date-fns, react-markdown, axios, socket.io-client, radix-ui/*, next-themes, lucide-react, @tabler/*, openai, @ai-sdk/*; anything else is refused at build with a message naming it. A client-side router is never the answer — a route is a FILE (src/pages/about.astro → /about). IMAGES AND BINARIES: set encoding:"base64" on the file and send the bytes — that is how you put a logo, a photo, an OG image, a favicon or a font on the site (png/jpg/webp/svg/ico/mp4/woff2/pdf, 512KB max each decoded). Without it you can only write text, and a site with no images looks unfinished. To ADD an image from a text prompt WITHOUT sending any bytes (a real photo's base64 is too big to emit reliably), use generate_image — Kleap generates it and stores it for you. To REMOVE a page or asset, use delete_files — overwriting it with empty content leaves a URL that answers 200 with nothing, which is worse than a 404. DATA & ACCOUNTS: write_files only STORES files — it cannot provision the Kleap Database, so DB or auth code pushed here has no backend and silently does nothing. Stand the feature up with modify_app first, then edit those pages here. After writing, call publish_app to build & go live.
    Connector
    Destructive
    No auth
  • Given 2-5 candidate packages for the same job (e.g. "axios vs got vs node-fetch"), fetches the same registry/popularity/maintenance/vulnerability enrichment get_package computes for each one in parallel and returns a structured side-by-side plus a deterministic, reasoned pick. Each candidate gets downloads + trend, popularityTier/maintenanceTier, GitHub stars, TypeScript support, license, deprecated status, latest-version vulnerability status, a lightweight installScriptRisk signal (scans lifecycle script command strings for known red flags — does NOT fetch the tarball; call analyze_install_script on a specific candidate for that deeper scan), and installSize (the candidate's own dist.unpackedSize plus a transitive rollup — summed dist.unpackedSize across its resolved dependency tree, walked up to depth 2 / 60 nodes per candidate; `installSize.transitive.truncated`/`sizeUnknownCount` flag when that sum is partial rather than pretending it's exact — call analyze_transitive_dependencies on a specific candidate for the full graph). `differentiators` names which candidates stand out on each dimension (most downloads, only ones with TS types, which are deprecated/vulnerable/flagged as a typosquat/install-script risk, smallest/largest install size). `recommendation.pick` is chosen deterministically from a weighted score (popularity, maintenance, deprecation, vulnerabilities, typosquat flag, install-script risk, TS support, GitHub stars — install size is reported but not scored) — never a deprecated or typosquat-flagged candidate — with `rationale` explaining why and `confidence` reflecting how close the top two scored. If a candidate's OSV.dev vulnerability check itself failed (network/timeout/upstream outage), `isLatestVersionVulnerable` comes back `false` only because the field has to be a boolean — `vulnerabilityCheckFailed:true` is the real signal there, and means that candidate's safe/not-safe answer is unknown, not confirmed clean. A name that can't be resolved (typo, unpublished, malformed) still appears in `candidates` with `found:false` and `resolutionError` set rather than failing the whole call; duplicate names in the input are rejected.
    ConnectorNo auth
  • Given 2-5 candidate packages for the same job (e.g. "axios vs got vs node-fetch"), fetches the same registry/popularity/maintenance/vulnerability enrichment get_package computes for each one in parallel and returns a structured side-by-side plus a deterministic, reasoned pick. Each candidate gets downloads + trend, popularityTier/maintenanceTier, GitHub stars, TypeScript support, license, deprecated status, latest-version vulnerability status, a lightweight installScriptRisk signal (scans lifecycle script command strings for known red flags — does NOT fetch the tarball; call analyze_install_script on a specific candidate for that deeper scan), and installSize (the candidate's own dist.unpackedSize plus a transitive rollup — summed dist.unpackedSize across its resolved dependency tree, walked up to depth 2 / 60 nodes per candidate; `installSize.transitive.truncated`/`sizeUnknownCount` flag when that sum is partial rather than pretending it's exact — call analyze_transitive_dependencies on a specific candidate for the full graph). `differentiators` names which candidates stand out on each dimension (most downloads, only ones with TS types, which are deprecated/vulnerable/flagged as a typosquat/install-script risk, smallest/largest install size). `recommendation.pick` is chosen deterministically from a weighted score (popularity, maintenance, deprecation, vulnerabilities, typosquat flag, install-script risk, TS support, GitHub stars — install size is reported but not scored) — never a deprecated or typosquat-flagged candidate — with `rationale` explaining why and `confidence` reflecting how close the top two scored. If a candidate's OSV.dev vulnerability check itself failed (network/timeout/upstream outage), `isLatestVersionVulnerable` comes back `false` only because the field has to be a boolean — `vulnerabilityCheckFailed:true` is the real signal there, and means that candidate's safe/not-safe answer is unknown, not confirmed clean. A name that can't be resolved (typo, unpublished, malformed) still appears in `candidates` with `found:false` and `resolutionError` set rather than failing the whole call; duplicate names in the input are rejected.
    ConnectorNo auth

Matching MCP Servers

  • A
    license
    B
    quality
    D
    maintenance
    A server based on Model Context Protocol that parses Swagger/OpenAPI documents and generates TypeScript types and API client code for different frameworks (Axios, Fetch, React Query).
    12
    10 npm
    16
    ISC
  • A
    license
    A
    quality
    D
    maintenance
    Free MCP server for Claude with math and financial calculation tools — unit conversion, currency math, compound interest, statistics.
    8
    2
    MIT

Matching MCP Connectors

  • Free agent-service discovery, OpenAPI document checks, and receipt verification. No API key needed.

  • Verified answers with named sources: UK parking appeals, NYC dismissal rates, UK MTD tax facts.

  • PAID (x402, 6 USDC): generate a production 3D avatar from a reference photo (base64) — xAI A-pose normalize → TRELLIS.2 GPU mesh → full canonical post-process. Payment settles ONLY when generation completes; a failed generation is never charged. Returns a job_id — poll with the free get_generation_status tool (typical runtime 5-15 minutes). Pass idempotency_key when a retry is possible (timeout/5xx) — replaying the same key returns the original job_id instead of a second GPU job/charge. [Paid: $6.00 USDC via x402 for unauthenticated calls on the hosted /mcp endpoint; DEFERRED settlement — charged only when the generation job completes, a failed job is never charged. Poll get_generation_status (free).]
    ConnectorNo auth
  • Given one package and two versions (from -> to), returns a structured upgrade analysis: semver classification, GitHub release notes summary, detected breaking changes, security advisories fixed in the range, migration guide links, and a clear recommendation. Use when the user asks about a specific package upgrade ('what changed between react 18 and 19', 'is it safe to bump axios from 0.27 to 1.0', 'what does upgrading lodash 4.17.20 to 4.17.21 fix'). Supports npm, pypi, and github-actions (use the action reference as the name, e.g. actions/checkout). For analyzing many packages at once or a Dependabot batch, use analyze_packages_bulk instead.
    ConnectorNo auth
  • Deploy or update a website or web app to get a public URL. Text files only in files[]. files[] must be a JSON array, even for one file. Example: files: [{"filename":"src/App.tsx","content":"..."}]. Never pass a bare string or a single file object. Use files[] for inline text edits and diffs, not for copying large existing local file contents into tool params. Never inline or base64-encode binary assets/resources in files[]; use upload_assets first for images, fonts, media, PDFs, archives, and other client-supplied file assets, then pass upload_id. Format generated and edited source files as conventional, human-readable multi-line code; never minify or collapse an entire file onto one line. For JavaScript/TypeScript/JSX/TSX string literals, use single quotes wherever valid. Template files from get_app_template are auto-included as the baseline — use diffs[] to modify them; content is otherwise only for entirely new files. New apps: tests/tests.json is the intentional template-file exception and must be sent as a complete content replacement. New apps: set app_id to null, provide app_name, description, app_type, frontend_template, and features. Updates: provide existing app_id, features, and either changed files/deletePaths or upload_id. If upload_id is provided, do not also send files[] or deletePaths[]; the upload manifest owns all text changes, diffs, and delete operations. Rules: do not add @appdeploy/client or @appdeploy/sdk to package.json (platform-injected). SPAs must use HashRouter. Frontend must never import @appdeploy/sdk; backend must never import @appdeploy/client. Frontend must use api from @appdeploy/client for backend calls, never fetch() or axios. If frontend realtime is used, @appdeploy/client websocket usage is ws.connect() only; do not call ws.subscribe/ws.publish/ws.send directly on ws. After deploy, poll get_app_status every 5s until status is 'ready' or 'failed'. On a lifetime-limit error, stop deploy_app calls unless the account limit increases. The limit does not reset; show the returned upgrade link to the user. If get_app_status returns QA/e2e/runtime errors, attempt automatic fixes and redeploy up to 3 times before asking the user for guidance.
    Connector
    Destructive
    OAuth
  • Search 35 plain-English answers about UK Making Tax Digital for Income Tax — thresholds and start dates (£50k Apr 2026 / £30k Apr 2027 / £20k Apr 2028), quarterly update deadlines, digital records, penalties, exemptions, sign-up, software. Every answer is sourced line-by-line to named GOV.UK/HMRC pages, re-checked 14 August 2026. Returns the matching questions with short answers; call get_mtd_answer for the full text and sources.
    ConnectorNo auth
  • One MTD answer in full: the question, the short answer, the complete plain-text body, the FAQ pairs, and every GOV.UK/HMRC source page the answer rests on. Use the slug from search_mtd_answers.
    ConnectorNo auth
  • Returns a ranked, deadline-aware list of open Base ecosystem funding programs (grants, accelerators, hackathons, retro-funding). Each result cites source_url, deadline, funding_range_usd, and last_verified_at. Stale entries are flagged. Designed for agents and builders shipping on Base who need a single call to surface the next applicable funding deadline.
    ConnectorNo auth
  • Returns invocation guidance for executing a paid extraction job after extract.estimate. Payment is x402 USDC on Base, amount equals cost_breakdown.price_usdc from the estimate (clamped onto the 5-tier ladder: $0.10 / $0.50 / $1.00 / $2.50 / $5.00). Result delivery: job_id + result + grade (A/B/C/D) + result_url. Grade D triggers 80% auto-refund. MCP cannot carry the X-PAYMENT header, so this tool returns the endpoint + price; execute the paid POST directly with an x402 client (x402-fetch, x402-axios).
    ConnectorNo auth
  • Returns a 0-100 JavaScript/npm ecosystem momentum score (weekly downloads of 8 bellwether packages — react, express, lodash, axios, typescript, next, vue, webpack — vs 3 prior weekday-aligned weeks; 50 = flat) with per-package volumes and WoW changes, total weekly downloads, top_package, and fastest_grower. Call when the user asks whether the JS/npm ecosystem is growing or cooling or which packages are moving, or when timing devtools launches or developer-marketing spend. Python: ADW-588. Updates: daily.
    ConnectorNo auth
  • Inspect an avatar's contract state and provenance chain (stage, bone/vertex counts, provenance step count, chain_valid + any broken links). Does not return a quality grade — use axis_validate for pass/warn/fail rule results. [Paid: $0.10 USDC via x402 for unauthenticated calls on the hosted /mcp endpoint; settled only on a successful (non-error) result.]
    ConnectorNo auth
  • How New York City parking and camera tickets are actually decided at hearing, violation type by violation type — the share dismissed outright and the share dismissed or reduced, computed from the City's own published hearing records (119.8M rows). Give a violation to get its rates (partial names match, e.g. 'SIDEWALK' or 'MUNI METER'); omit it for a ranking of all 80 violation types.
    ConnectorNo auth
  • One call for a denied US health-insurance claim: both free appeal clocks with your actual dates where they can be computed, which external-review route applies (state, federal, or the federal one regardless of your state because the plan is self-funded), what the CMS file records for external reviews filed and overturned in that state and for that insurer — or 'not reported' where the file does not carry it — the insurer's own published appeal procedure where we have read it, and your state insurance department's consumer line with the date we read it from their own site. Free, no key, attribution required. Source: CMS Transparency in Coverage Public Use File (PY2026 release), 45 CFR 147.136.
    ConnectorNo auth
  • Given a US tenant- or employment-screening company (Checkr, HireRight, First Advantage, Sterling, LexisNexis, ChexSystems, SafeRent, RentGrow, TransUnion Rental, AppFolio, RealPage, CoreLogic, Experian RentBureau, Early Warning), return that company's verified dispute route (portal URL, phone, email, postal address, each with the date it was read from the company's own site), the FCRA clock that applies after an adverse action (60 / 30 / 45 days, cited to statute), what the federal CFPB complaint record shows happened to people who complained about that company, and whether the screening company or the platform is the party that can actually fix the error. Free, no key, attribution required. Source: CFPB Consumer Complaint Database; narrative-derived counts cover 2011 - 14 Aug 2026, when the CFPB ceased publishing narratives.
    ConnectorNo auth
  • Read one canonical directory entry by slug, capability id, or stable directory id. No commercial obligation. Risk R0; PUBLIC.
    ConnectorNo auth
  • Search public service contracts by declared text and optional price ceiling without an opaque ranking score. No commercial obligation. Risk R0; PUBLIC.
    ConnectorNo auth
  • Score a whole group at once — every pairing rolled up into team cohesion, the weakest shared dimension, who is best connected, who is on the edge, the pairings to watch, and the role mix. Use instead of looping score_compatibility for three or more people. Billed at 2x a normal tool call.
    ConnectorNo auth