AXL MCP
Server Details
Turn one prompt into a live landing page and leads in your CRM. AXL MCP lets your AI agent build pages, capture leads, manage contacts, book calls, run email campaigns, and deliver courses.
Open-source agent skill. Powered by AXL, a hosted SaaS platform.
Skill and demo: https://github.com/axlhq/business-stack
Install the skill:
npx skills add axlhq/business-stackConnect MCP: https://app.axl.tech/mcp — sign in to your AXL account in the browser (OAuth 2.1). Installation and connection are separate steps.
First run — paste this into your agent:
Using AXL, build a landing page for my [offer] with a name-and-email form that saves each signup to the CRM. Show me a preview and ask before publishing. After I approve, publish it and give me the public and admin links. I will submit a test signup; then find that contact in the CRM and confirm the form answers were saved.
MCP setup: https://axl.tech/developers/mcp
Documentation: https://docs.axl.tech/mcp
Product overview (77 seconds): https://www.youtube.com/watch?v=jlhR9CafIww
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 16 tools
The set has several clusters (discovery, schema introspection, image handling, execution), but within each cluster the tools are cleanly bounded: capability_map is explicitly the router, list_modules/list_operations are drill-downs, and search_operations is scoped to API vocabulary. The schema tools each target a different artifact (operation, fields selector, extended filters, quiz items, scenario nodes) and check_scenario_node_payload is clearly validation vs. get_scenario_node_schema's description, so confusion is limited to choosing between the several discovery paths, which the descriptions mitigate with explicit precedence rules.
Nearly everything is snake_case verb_noun (get_*_schema, list_*, search_*, generate_image, invoke_operation, import_image_from_url), with the get_*_schema family forming a predictable sub-pattern. The main deviation is capability_map, a bare noun naming an entry point rather than an action, and the schema getters vary in subject granularity (get_fields_schema vs get_extended_filter_schema), but conventions are never mixed.
At 16 tools it sits just above the comfortable band, but the surface is disciplined: a single invoke_operation fronts the entire Admin API, so breadth is handled by discovery rather than per-endpoint tools. Every tool maps to a distinct need (routing, discovery, five schema introspectors, validation, three image operations, docs search), with little obvious redundancy.
The generic invoke_operation plus capability_map/list_operations/search_operations/search_docs/get_operation_schema gives lifecycle-wide coverage of any API operation, and schema introspection covers the awkward opaque-string artifacts (quiz SettingsJson, scenario node payloads) including a dry-run validator. Minor gaps remain: payload validation exists only for scenario nodes (no equivalent dry-run for general write bodies) and there is no explicit pagination/result-follow-up helper, but agents can work around both.
Available Tools
16 toolscapability_mapARead-onlyInspect
CALL THIS FIRST, before any other tool. Orientation map of the whole Admin API: the platform-wide conventions you cannot see from a schema, and six task areas — each listing what users ask for, the literal first calls that serve those requests, and the cross-module traps that would otherwise send you to the wrong module. Module names are namespace segments and several of them lie about their contents, so routing by name alone fails. Pass 'area' for that area's modules (purpose, gotcha, recipes) and its FULL trap list — the overview carries only the first two traps per area.
Inputs: area.
check_scenario_node_payloadARead-onlyInspect
Dry-run a scenario node 'payload' against its config class BEFORE writing it: reports unknown/misspelled properties and type mismatches, and returns the normalized JSON. Read-only — nothing is created or changed. Worth calling for any node type whose get_scenario_node_schema card says validation=NONE, because there the server accepts a broken payload silently and the node only misbehaves once a contact reaches it.
Inputs: payload (required), actionType (required).
generate_imageAInspect
Generate a BRAND-NEW image via Gemini; stores it and returns image_url (+ markdown preview). Billed — REQUIRES confirmSpend=true after a REAL human yes in a SEPARATE message. STANDALONE: omit sitePageId → account-root AI folder; after success SHOW the image. PAGE/SITE: forPage=true AND sitePageId= → Sites/{site}/{page}/AI; propose prompt+quality+charge first, then place the URL on the page. quality: standard/high/premium. On aiSpendExhausted: warn + Billing — do not retry.
Inputs: prompt (required), style, forPage, quality, +2 more.
get_extended_filter_schemaARead-onlyInspect
Format of extended filters ('extendedFilter' property of list filters): envelope, condition enum and filter types. Without arguments returns the full type catalog; 'search' filters it; 'filterType' returns the payload JSON schema of one type.
Inputs: search, filterType.
get_fields_schemaARead-onlyInspect
Exact set of fields supported by the operation's 'fields' selector (GraphQL-like syntax: '{id, firstName, avatar{id, cloudKey}}'), respecting the current admin's rights. Returns the root entity's scalar fields in full; nested entities are stubs marked expandable=true — expand one by re-calling with 'path'.
Inputs: operationId (required), path.
get_operation_schemaARead-onlyInspect
Full schema of one operation: parameters, request body (schema + example) and responses, plus 'hints' and any matching 'recipes'. Nested schemas are inlined up to depth 4; deeper objects are marked truncated. Large schemas are trimmed to fit — use section='request'/'response' to fetch one part in full.
Inputs: operationId (required), section.
get_quiz_item_schemaARead-onlyInspect
Quiz/form item types and the shape of their 'SettingsJson' — a STRINGIFIED JSON object whose keys depend entirely on the item's 'Type', which the OpenAPI schema cannot show (it types the property as an opaque string). CALL THIS BEFORE creating or updating ANY form item: the server stores SettingsJson verbatim, never fills a default and never validates a key, so a guessed blob is saved with HTTP 200 and only breaks in the respondent's browser — and it must never be null or empty, not even for a separator. Without arguments returns the shared base settings, the conventions and the traps; 'category'/'search' list types; 'itemType' returns one type's full settings card with a ready-to-send example and the system contact attributes it may be bound to.
Inputs: search, category, itemType.
get_scenario_node_schemaARead-onlyInspect
Scenario node types and the JSON schema of their polymorphic 'payload' config — the shape the OpenAPI schema cannot show (it types 'payload' as an opaque string). CALL THIS BEFORE creating or configuring ANY scenario node: the server fills a default payload only for events and listeners (every ACTION comes back null) and type-checks only 13 of 137 node types, so a guessed payload is stored with HTTP 200 and breaks at run time. Without arguments returns the graph model and workflow; 'kind'/'search'/'outputs' list node types (outputs='fail' answers "which steps can I attach error handling to?"); 'actionType' returns one node's payload schema, default payload and — critically — which link types it routes to; 'scenarioId' returns the trigger events THAT scenario accepts.
Inputs: kind, search, outputs, actionType, +1 more.
import_image_from_urlAInspect
Import an EXTERNAL http(s) image into account storage (no Gemini charge). Returns image_url (+ preview). Optional sitePageId → Sites/{site}/{page}/AI; omit → account-root AI. SSRF-guarded.
Inputs: url (required), name, sitePageId.
invoke_operationADestructiveInspect
Execute an Admin API operation through the standard HTTP pipeline (caller's token, account context and permissions apply). Success returns {success: true, body: ...}; an API error returns {success: false, errors: [{code, type, message, hint?}]} (statusCode added only when not 200); a guard refusal returns {error, details?}.
Inputs: body, confirm, guideAck, pathParams, +2 more.
list_modulesARead-onlyInspect
Flat index of every Admin API module: operation count, the area it belongs to, what it owns and its known trap. This is a drill-down, NOT the entry point — call capability_map first to route a request to an area, then use this to see every module or list_operations(module) for one module's operations.
Inputs: no named parameters.
list_operationsARead-onlyInspect
List operations of one API module: operationId, HTTP method, path, summary. Paginated by 100. Optional 'search' filters within the module (every word must match operationId, path or summary). Module names come from capability_map (which also says what each module owns and where its traps are).
Inputs: module (required), page, search.
list_recipesARead-onlyInspect
Ready-made, VERIFIED recipes: intent -> operationId + a correct example body + notes on non-obvious conventions the schema can't show (e.g. 'a new tag is created only when id == text', or 'this endpoint adds, the *.Update endpoint replaces'). capability_map names the recipe for a task as 'recipe:' — fetch it here with search= before building that call by hand. Search is AND over every word, so ask for ONE intent per call ('upload_file', then 'create_landing_site') — bundling several returns nothing. With 'search' the closest few come back in FULL (an exact intent match always among them) and any further matches as stubs — intent + operationId, usually all you need; without 'search', lightweight stubs of every recipe. A recipe that CREATES something also carries 'deadUnless': the surface a real client meets that artifact on and the connection that makes it work. Treat it as part of the job — most things here are invisible until something a visitor actually opens carries them, and the same text comes back on the invoke_operation result that creates one.
Inputs: search.
regenerate_imageAInspect
Edit/restyle an existing image; stores a NEW file and returns image_url (+ markdown preview). Does NOT patch site HTML. Billed — REQUIRES confirmSpend=true. PAGE/SITE: forPage=true + sitePageId; propose edit+quality+charge first. STANDALONE: show the new image.
Inputs: edit_instruction (required), source_image_url (required), forPage, quality, +2 more.
search_docsARead-onlyInspect
The AXL product documentation (docs.axl.tech, the knowledge base an admin reads) — searchable, and readable in full. Use it for PRODUCT questions the API surface cannot answer: what a feature is, which flow it belongs to, what the business rules are, what the UI calls the thing the user just asked about, whether the platform can do X at all. It does NOT document the API — for operations, bodies and field semantics use capability_map / list_recipes / get_operation_schema. TWO STEPS: (1) search_docs(query="…") returns a ranked shortlist — title, UI section, the article's own summary, a matched snippet — and NOT the articles; (2) pick what looks relevant and call search_docs(slugs="slug-a,slug-b") to read those in full. Call with no arguments for the section outline, or section="CRM" to list one section. Articles are English-only.
Inputs: limit, query, slugs, section.
search_operationsARead-onlyInspect
Search operations across all API modules. Every word of the query must match the operationId, path, module, summary or a request-body property name (order-insensitive). Results are ranked by relevance; zero results include which words didn't match. It matches API vocabulary, not business vocabulary — if the request is phrased the way a user would phrase it, capability_map routes it faster; come here when no area fits or you already know the API's word for it.
Inputs: query (required), limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Build and deploy sales funnels from your AI agent, with checkout, upsells, CRM and email wired
Orbit is an MCP server that gives your AI agents a 4000+ tools, a shared memory brain and a live dashboard OS. Every agent reads active decisions, logs outputs to a searchable vault, and reports status in real time. 2-minute setup via MCP; works across Claude, ChatGPT, Codex, Cursor, Gemini, and Manus. Finally Agents work, agents that grow your business and bring you customers. https://orbitagents.xyz
Agent Commerce MCP — agent-native A2A storefront. Discovery, Stripe checkout, affiliate program.
Build, publish, capture leads from, measure and improve landing pages from your AI assistant.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMCP server and Claude skills for AI agents to build landing pages, run A/B experiments, and track first-party conversions. Lets agents onboard clients, create and publish pages, manage variants, and pull performance reports via the UXON API.11MIT

@seldonframe/mcpofficial
AlicenseNot gradedqualityCmaintenanceEnables MCP-compatible agents to build and operate complete AI front offices for local businesses—branded websites, booking, intake, CRM, and AI agents in one workspace.70AGPL 3.0
agentreadycrmofficial
AlicenseAqualityBmaintenanceEnables AI agents to manage a full CRM: resolving and creating organizations and contacts, logging interactions, moving deals through pipelines, and recording signals and proof points backed by quotes and URLs. Data lives in a local SQLite file or a hosted team service, with the same tools, views, and skills in both.461MIT- AlicenseNot gradedqualityDmaintenanceProvides AI agents with 220+ tools for building websites, sending email, managing contacts, invoicing, databases, automation, and more through a single secure connection. Features hardware-bound authentication and works with Claude Desktop, Claude Code, Cursor, and other MCP-compatible clients.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.