Cerell-mcp
A local stdio MCP gateway that lets AI coding agents compare, provision, connect, and manage infrastructure partners while tracking cashback — all through one infra(mode, request) tool.
Compare partners (
compare): search curated database/auth/hosting/email/cache etc. partners with live pricing and cashback rates; usedetail=1,limit=N,offset=Nfor more.Provision resources (
provision): trigger partner provisioning actions, e.g. create a database with region/name.Connect/disconnect accounts (
connect,disconnect): link partner API keys and plans.Check stack status (
status).Optimize the stack (
optimize).Evolve/migrate (
evolve): compare and move from one partner to another, e.g.from=neon to=supabase.Manage cashback (
cashback): view earnings or set payout details.Open partner portal (
portal).Supports affiliate signup links and lazy-started upstream partner MCPs when linked and needed.
Integrates with Clerk for authentication services, allowing comparison, provisioning, connecting API keys, and managing auth infrastructure as part of the infra workflow.
Integrates with Resend for email services, supporting comparison, provisioning, and operational management via the infra tool.
Supports developer cashback payouts via Revolut, allowing cashback requests with amount and Revtag through the cashback mode.
Integrates with Supabase as a database and backend platform, supporting comparison and migration (e.g., evolve from Neon to Supabase) through the infra tool.
Integrates with Upstash for Redis and Kafka services, enabling comparison, provisioning, and connection management through the infra tool.
Integrates with Vercel for deployment and hosting, enabling comparison, provisioning, and connection management through the infra tool.
Cerell MCP — Infrastructure Copilot & Developer Cashback
Mission
The decision about which database, hosting, or auth service goes into a project no longer happens in a browser tab -- it happens inside an AI coding agent. Cerell is built for exactly that moment, and it solves two problems at once.
For developers: AI-assisted coding is expensive. Running agents through Cursor, Claude, or Windsurf burns real money in LLM tokens -- often $60-100/month for daily users. Cerell subsidizes that cost. When your agent suggests a partner service (a database, an email provider, a cache layer) and you accept it, the partner co-funds the tokens used in your session. You also earn cashback on your monthly cloud spend with that partner, credited back to your Cerell account. You build faster, you spend less.
For SaaS partners: Developer tools spend millions acquiring customers who sign up and never activate. Credits are handed out blind. Ads are clicked and forgotten. Cerell flips the model -- partners pay only when their product is actually wired into a developer's repository, after the developer explicitly accepted the suggestion. The conversion event is the install in the repo, not a pageview, not a form submission. That is a fundamentally different -- and cheaper -- unit of acquisition.
How it works in practice:
Your AI agent asks to add a database (or auth, hosting, email, cache...).
Cerell surfaces a curated partner match with live pricing and cashback rate.
You review, see the alternatives, and accept or skip -- your choice, always.
On accept, the upstream partner MCP provisions the resource and returns credentials directly to your environment.
The partner is billed for the install. You earn cashback. The session cost is co-funded.
One action. Two problems solved.
Related MCP server: OpenAPI Doctor
Agenda
Close the gap between AI suggestion and real adoption. MCP registries offer discovery; Cerell adds distribution, attribution, and economics.
Make infrastructure decisions transparent. Every partner suggestion is labeled. Alternatives are always shown. Nothing is installed without the developer accepting.
Align incentives across the stack. Partners pay for activated integrations. Developers earn back a share of what they spend on cloud. The platform takes a margin only when value is delivered.
Stay editor-agnostic. Cursor, Claude Code, Windsurf, VS Code -- the same
infratool works everywhere, keeping the acquisition channel neutral and trustworthy for partners who do not want to depend on a single IDE vendor.Grow the catalog without growing complexity. Partners are added as JSON files in
data/partners/. The MCP tool surface stays constant -- one tool, every category.
Local stdio meta-tool gateway for Cursor, Claude Code, Windsurf, and VS Code.
One tool — infra(mode, request) — covers compare → provision → connect → operate/optimize/evolve → cashback, while keeping affiliate signup links in the path.
Quickstart
git clone https://github.com/Pawelec12/cerell-mcp.git
cd cerell-mcp
npm install
npm run buildCursor (.cursor/mcp.json)
{
"mcpServers": {
"cerell": {
"command": "node",
"args": ["C:/path/to/cerell-mcp/dist/index.js"]
}
}
}Claude Code
claude mcp add cerell -- node /ABSOLUTE/PATH/TO/cerell-mcp/dist/index.jsTool: infra
Arg | Meaning |
|
|
| Free text / tokens. Flags: |
Replies are compact JSON by default ({"ok":true,...}). Add detail=1 for full pricing, actions, docs, migration steps.
Examples
mode=compare request="database postgres"
mode=compare request="auth detail=1 limit=10"
mode=provision request="neon"
mode=connect request="neon api_key=YOUR_KEY plan=Launch"
mode=provision request="neon create_database name=app region=aws-eu-central-1"
mode=status request=""
mode=optimize request=""
mode=evolve request="from=neon to=supabase detail=1"
mode=cashback request=""
mode=cashback request="amount=25 method=revolut revtag=@you"
mode=portal request=""Flow after you pick a partner: signup (affiliate URL) → connect API key → provision action → cashback tracking.
Partner upstream MCPs (optional upstream in partner JSON) start lazily only when linked and an action needs them (max 3 live connections, LRU).
Partners
Configured in data/partners/*.json (Neon, Clerk, Upstash, Resend, Vercel, …). Catalog size does not grow the MCP tool list.
Publish on Smithery (local / MCPB)
Do not paste the GitHub URL into Smithery’s “MCP Server URL” field. Cerell is stdio-local.
npm run pack:mcpb
# → cerell.mcpb
npx @smithery/cli mcp publish ./cerell.mcpb -n apptent/cerellThat matches Smithery’s Local (MCPB Bundle) flow: users download the bundle and run it on their machine.
Dev
npm run build
npm test
npm run pack:mcpb
npm run inspectorLicense
Available Tools
1 toolinfraC
Cerell infra gateway: compare/provision/connect partners, status/optimize/evolve stack, cashback/portal. Compact JSON; add detail=1 or limit=N in request for more.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | Yes | compare|provision|connect|disconnect|status|optimize|evolve|cashback|portal | |
| request | Yes | Free text or tokens. Flags: detail=1 limit=5 offset=0. Ex: "database postgres", "neon create_database name=app", "neon api_key=sk", "amount=25 method=revolut revtag=@x" |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations, so the description carries the full burden. It does disclose output behavior (compact JSON by default, expandable via detail/limit), which is genuine value. However, it says nothing about the side effects, permissions, or reversibility of the mutating modes (provision, connect, disconnect, optimize, evolve) — a serious omission for a gateway that can change infrastructure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the mode inventory and ending with the response-shaping hint. It is dense but every clause is doing something, though the slash-separated verb chains read as shorthand rather than prose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
This is a 9-mode gateway funneling everything through one free-text field with no output schema, and the description never explains what shape the request should take per mode beyond brief schema examples. For a tool with this much behavioral surface, the description is under-specified.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the schema already documents both mode (enum) and request (with example strings and flags). The description repeats the mode list and the detail/limit flags without adding per-mode request format guidance, so baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Identifies the tool as a gateway and pairs each mode with a rough noun (partners, stack, cashback/portal), so an agent knows it is a multi-mode infra multiplexer. But the mode-to-task mapping is telegraphic slash-lists, and 'infra' plus verbs like 'evolve' don't tell the agent concretely what any single mode does.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The only actionable guidance is 'add detail=1 or limit=N in request for more', which governs response verbosity rather than tool/mode selection. Nothing explains when to pick compare versus status, or whether provision/connect require prerequisites; the agent must guess at mode choice. No siblings exist, so no alternative routing is needed, but mode selection guidance is absent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v0.1.0- First observed
infra
TDQS
Scored across 1 tool
With only one tool, there is no cross-tool overlap or misselection risk. However, the single tool bundles many distinct operations (partners, stack, cashback, portal), so agents must disambiguate through parameters rather than tool choice.
There is only one tool name, so consistency cannot be meaningfully evaluated. The name 'infra' is broad and does not follow a verb_noun pattern, but it is readable.
The apparent scope spans partner provisioning, stack optimization, evolution, cashback, and portal operations. Collapsing all of that into one mega-tool is too thin for the domain and forces excessive reliance on parameter conventions.
The description mentions several major capability areas, suggesting broad coverage, but the surface lacks granular operations and clear CRUD/lifecycle boundaries. Agents may work around this with the detail/limit parameters, but specific workflows are opaque.
Maintenance
Related MCP Connectors
Personal MCP server for humans who create. Proof of authorship, license control.
MCP server for Pinchwork - an agent-to-agent task marketplace with credits-based economy
Official MCP server for Certifier to issue, manage, and track certificates and badges.
Marketplace and infrastructure for MCP servers and skills: deploy, host, monetize, analytics.
Related MCP Servers
- AlicenseAqualityDmaintenanceThis MCP server assists Minecraft Java plugin developers by providing dependency documentation lookups, version checking, and automated scanning for Gradle and Maven projects. It supports popular APIs such as Paper, Spigot, and LuckPerms to streamline plugin development and workspace analysis.43MIT
- AlicenseAqualityCmaintenanceA template for building MCP servers with a built-in paywall gate that offers free local execution and premium server-side execution via Stripe and x402 payment lanes.1MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that gates content and tools behind x402 stablecoin micropayments with pluggable content and payment network adapters.MIT

OrcaRail MCPofficial
AlicenseBqualityAmaintenanceOfficial MCP server for accepting crypto payments through OrcaRail. It enables AI agents to create payment intents, manage subscriptions, handle product catalogs, and get exchange rates via natural language.26217 npmMIT