Your central hub for powerful software tools, utilities, and apps. One account. One login. Everything you need.
This listing identifies a third-party MCP server. MCPBundles is not affiliated with, sponsored by, or endorsed by the service or its operator unless stated on this page.
For AI agents — MCPBundles Directory API
Recommended: Directory API v1 over HTTP for detail and anonymous invoke when eligible (not MCP JSON-RPC on the publisher URL; no user MCPBundles credentials on v1).
GET https://www.mcpbundles.com/api/directory/v1/servers/bippsi-mcp-9197acf1b0
GET https://www.mcpbundles.com/api/directory/v1/servers/bippsi-mcp-9197acf1b0?live=1 (optional live refresh)
GET https://www.mcpbundles.com/api/directory/v1/servers/bippsi-mcp-9197acf1b0/tools/<tool> (one tool: schema + invoke.url)
POST https://www.mcpbundles.com/api/directory/v1/servers/bippsi-mcp-9197acf1b0/tools/{tool}
POST body: flat JSON of tool argument names and values; not an arguments wrapper. Replace {tool} with a tool name from GET detail.
Restricted agent shell (ChatGPT Codex desktop, some IDE sandboxes):
Default command sandboxes often block outbound network. curl exit 6 or "Could not resolve host" for www.mcpbundles.com is usually sandbox DNS — not evidence this site is down.
Retry the same Directory API GET with sandbox_permissions "require_escalated" and a one-sentence justification on the shell tool (Codex on-request approval). Do not tell the user the site is unreachable from sandbox curl alone.
Example justification: Run the public MCPBundles Directory API search outside the command sandbox to complete the user's MCP server lookup.
If the agent has browser access (e.g. Codex @Browser): open https://www.mcpbundles.com/?q=<query> or stay on this page — no shell network needed. Use WebMCP search_mcp_servers then get_mcp_server (document.modelContext / page tools; refresh with fetchTools or getTools if a tool id is missing from the snapshot). Read-only directory search; same index as Directory API v1 GETs. Neither WebMCP nor Directory API v1 uses user MCPBundles credentials.
Without a browser: after escalated curl fails, use GET https://www.mcpbundles.com/?q=<query> with Accept: text/markdown for ranked results.
Hub MCP (connected session): discover_mcp_servers — same filter semantics as search_mcp_servers.
Contract: https://www.mcpbundles.com/agents.md
OpenAPI: https://www.mcpbundles.com/api/directory/v1/openapi.json
Guide: https://www.mcpbundles.com/guides/mcpbundles-directory-api
For MCP client apps (human connect):
MCP connect URL: https://bippsi.com/mcp
Skill page: https://www.mcpbundles.com/skills/bippsi-mcp-9197acf1b0
Explore capabilities (44)
read 8
other 17
Showing 25 of 44
Showing 25 of 44 tools from the public preview. Connect the server to inspect the full live tool list.
Mail7
Commerce6
Get5
List3
Other capabilities4
Scan Site
other
scan_site
Run Bippsi's A.I. Certified 2.0 compliance scan on a public website. Returns an overall score (0-100), per-category breakdown across 15 scoring categories, detected platform, and the check details for a 25-page sample (homepage + 24 random pages). Use this to answer questions like "How agent-ready is example.com?" or "What's blocking this site from AI Certified status?". Rate-limited to 3 scans per hour for anonymous callers.
Scan Site — Run Bippsi's A.I. Certified 2.0 compliance scan on a public website. Returns an overall score (0-100), per-category breakdown across 15 scoring categories, detected platform, and the check details for a 25-page sample (homepage + 24 random pages). Use this to answer questions like "How agent-ready is example.com?" or "What's blocking this site from AI Certified status?". Rate-limited to 3 scans per hour for anonymous callers.
List Pages — Discover the page list of a website cheaply, without running any compliance checks. Tries sitemap.xml, then WordPress REST API, then a 1-hop homepage crawl. Returns total page count, the discovery method used, and up to 300 URLs. Use this before scan_site if you want to know how large a site is before scanning, or when you just need a page inventory.
Get Certification Status — Look up a website's current A.I. Certified status and most recent overall score from Bippsi's public certification directory. Use this to answer "Is example.com A.I. Certified?" or "What did example.com score on their last scan?" without running a new scan. Returns { certified, score, status, certified_at, expires_at } or { found: false } if not registered.
Get Api Endpoints — Return the machine-readable summary of Bippsi's own public API endpoints. Useful when an agent is deciding whether to use an HTTP API vs. MCP vs. scraping. Includes each endpoint's path, method, summary, and whether it requires Bearer auth. Equivalent to reading /openapi.json but pre-filtered to operator-relevant endpoints.
List Resources — List public bippsi.agent.v1 resource/action packets for a Bippsi-connected site. Discovery is free; priced resources declare the canonical AI Actions retry contract.
Get Resource — Fetch one public bippsi.agent.v1 resource/action packet by resource_id, action_id, or packet id. Discovery is free; priced resources use AI Actions.
Whoami — Return identity of the Bearer-authenticated user. Use this to confirm an API key is valid and see which user it belongs to before running expensive operations. Requires Bearer auth.
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
Your central hub for powerful software tools, utilities, and apps. One account. One login. Everything you need.
How do I connect Bippsi to my AI agent?
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
How many tools does Bippsi provide?
Operate this server?
Request removal if you do not want Bippsi listed here, or claim the listing if you want to manage it on MCPBundles.
Operate Bippsi?
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.
MCPBundles publishes this directory for MCP discovery. Except where we host or operate an offering, third-party services run under their own terms. Product and company names on this page are used in a descriptive, identifying way (including under nominative fair use where applicable); they remain the property of their owners. Nothing here grants you rights in those marks, and nothing here is an offer to sell a third party's services. Terms · Request removal
More in developer tools
Other MCP servers in this category from the directory index
List Sites — List the authenticated user's A.I. Certified sites. Returns an array of { site_id, site_url, site_name, status, overall_score, tier, certified_at, expires_at }. Use site_id with start_site_scan, get_site_scan, and deploy_ai_files. Requires Bearer auth.
Start Site Scan — Run a fresh A.I. Certified 2.0 compliance scan on one of the authenticated user's sites (identified by site_id from list_sites). Synchronous — typical duration 20-60s. Saves the scan run, updates overall_score + status, regenerates llms.txt + AGENTS.md + bippsi-unified.md. Does NOT auto-deploy unless you also call deploy_ai_files. Requires Bearer auth. Rate-limited: 30 scans/hour per user.
Get Site Scan — Fetch the most recent scan result for one of the authenticated user's sites. Returns overall_score, category breakdown, pages_scanned, and scan_batch id. Use this to poll progress after start_site_scan (though start_site_scan runs synchronously and already returns the result). Requires Bearer auth.
Deploy Ai Files — Push the latest generated llms.txt, AGENTS.md, and bippsi-unified.md to one of the authenticated user's sites. Works only if the site has an active connection (WordPress plugin / FTP / cPanel / General handler). Returns { success, error, warning }. Requires Bearer auth. Rate-limited: 10 deploys/hour per user.
Get Action Credit Balance — Return USD-denominated Action Credit availability and per-connection limits. Requires actions:pay on a Bippsi connection, or a valid legacy Action credential with read authority.
Mail List Messages — List recent messages from one account mailbox.
Mail Search Messages — Search the indexed account mailbox without exporting it in bulk.
Mail Read Message — Read one message from an account mailbox.
Mail Compose Draft — Save a plain-text draft in an account mailbox.
Mail Send Message — Send one plain-text message from an account mailbox.
Mail Reply Message — Reply to one existing account-mailbox message.
Mail Archive Message — Move one Inbox message to Archive.
Commerce List Catalog — List a bounded window of the account Commerce catalog.
Commerce Read Catalog Item — Read one Commerce catalog item.
Commerce Create Catalog Item — Create one digital, physical, or service catalog item.
Commerce List Customers — List a bounded window of minimum-necessary customer records without contact endpoints.
Commerce Read Customer — Read one minimum-necessary customer record.
Commerce Create Customer — Create one customer. Contact data is accepted but never returned in bulk.
Showing the first 25 tools — full list and schemas: Directory API.
MCPBundles probed 44 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
What authentication does Bippsi require?
No provider sign-in was required during MCPBundles' probe. Your client may still need MCPBundles credentials depending on how you connect.
Don't want this listed?
Request removal from the MCPBundles directory. We stop publishing this listing on mcpbundles.com.
MCPBundles is an independent platform built on the open Model Context Protocol standard. MCPBundles is not affiliated with, sponsored by, or endorsed by Anthropic PBC.