Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
OCPI versions, checks and payload validation, plus your own test runs and run starts with a key.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
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:
https://mcp.chargerdojo.comRun this in your terminal
claude mcp add --transport http ocpi https://mcp.chargerdojo.comPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"ocpi": {
"url": "https://mcp.chargerdojo.com"
}
}
}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.
Paste into .vscode/mcp.json in your project
{
"servers": {
"ocpi": {
"type": "http",
"url": "https://mcp.chargerdojo.com"
}
}
}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:
https://mcp.chargerdojo.comMenu 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.
Tool names and descriptions exactly as the server reported them on Nov 6, 2026. The maker wrote them, not us; we show them as plain text.
chargerdojo_describe_accessExplain what this server can do, which tools are open to anyone, which need your ChargerDojo account, and each plan with its price and what it unlocks. Answers: what can I do here, what does my plan include, and how do I connect my account.
chargerdojo_list_ocpi_versionsList the OCPI versions ChargerDojo covers, with what each one is for and which modules are implemented. Answers: which OCPI versions can I test against.
chargerdojo_get_ocpi_versionDescribe one OCPI version: how the credentials token is encoded, whether endpoints split into sender and receiver, which modules are implemented, and what the known limits are. Answers: how does this OCPI version work on the wire.
chargerdojo_compare_ocpi_versionsCompare two OCPI versions: what changed in the protocol between them, and which modules ChargerDojo gained. Answers: what changes when I move from one OCPI version to another.
chargerdojo_list_journey_templatesList the OCPI charging journeys, each with the role it tests, its OCPI versions, the modules the endpoint must offer, the plan it needs against your own endpoint, and how long it runs on the sandbox. Filter by version and role. Answers: which journeys test my role at my OCPI vers
chargerdojo_get_usageReport the plan on this account and how much of each ceiling is left: targets, API keys, runs in flight, run rate and report retention. Answers: which plan am I on, and how close am I to its limits.
chargerdojo_list_targetsList the OCPI endpoints registered on this account, 25 a page, with each one's OCPI version, roles and registration status, or read one by id. Answers: which endpoints can I run against.
chargerdojo_list_runsList the conformance runs and charging journeys on this account, newest first and 25 a page, with their status and pass and fail counts, narrowed by target, status or OCPI version. Answers: what ran recently, and how did it go.
chargerdojo_list_conformance_suitesList the OCPI conformance suites that can be run, grouped by version and module, with how many checks each carries. Answers: what does a conformance run check at my OCPI version.
chargerdojo_get_run_verdictRead the verdict of one conformance run or charging journey on this account: how many checks passed, failed and warned, and whether anything graded at all. Answers: did this run pass.
chargerdojo_list_checksList the checks a conformance run of one OCPI module grades at one version: each check id, what it sends, each rule as required or optional with its strength, and the clause of the OCPI spec each rule is graded against, quoted. Answers: what will ChargerDojo hold my module to, an
chargerdojo_validate_payloadCheck one OCPI object, sent as JSON text, against the schema ChargerDojo grades that object with at one OCPI version, and list each field that breaks it. The JSON leaves your machine and is sent to chargerdojo.com; it is not stored or logged. Up to 64 KB, 30 calls a minute. Answe
chargerdojo_get_run_checksRead the checks of one conformance run on this account that failed, could not be graded or carried a warning, each with the rule it broke and the clause of the OCPI spec it was graded against, quoted. Answers: why did this run fail, and what does the spec say.
chargerdojo_compare_runCompare one conformance run with the previous comparable run against the same endpoint, OCPI version and module: which checks newly fail, which recovered, and which stopped being graded. Answers: what changed since my last run.
chargerdojo_get_scheduleRead the recurring run set on one target: its cadence, whether it is on or paused and why, when it runs next, and what its last run found. Schedules are set in the app, on the Automate plan. Answers: is my endpoint tested on a schedule, and did its last run pass.
chargerdojo_get_journey_eventsRead what happened during a charging journey on this account, step by step, with which assertions passed at each step. Answers: what happened at each step of this journey.
chargerdojo_cancel_runStop a charging journey that is still running on this account. It stops at the next safe point and keeps whatever it already graded. Answers: how do I stop a journey that is still running.
chargerdojo_list_runnable_journeysList the charging journeys that can run against one target on this account, say why the target supports them, and name the plan any of them needs that this account does not have. Answers: which journeys fit this endpoint, by its role and version.
chargerdojo_run_sandbox_journeyRun an OCPI charging journey against a sandbox endpoint. Answers: how do I try a journey without an endpoint of my own.
chargerdojo_run_journeyRun an OCPI charging journey against an endpoint registered on this account, the sandbox or your own, and return its report id. Against your own endpoint it needs the Integrate plan, and a few journeys need a higher one, which chargerdojo_list_journey_templates names. Answers: do
chargerdojo_start_conformance_runStart a conformance run against an endpoint registered on this account, the sandbox or your own: one module, or every module the endpoint offers. Returns the report id at once. Against your own endpoint it needs the Integrate plan, and a module sold on a higher plan names it. Ans
chargerdojo_send_feedbackSend a message to the people who build ChargerDojo: something missing, a bug, a question, or a verdict the person believes is wrong. Returns a reference.
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 7, 2026
The registry lists no source repo, so we cannot match the publisher (chargerdojo.com) to the code
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 801 ms (HTTP 200)
No sign-in needed
Read 22 tool descriptions and found no hidden instructions to the AI
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 2 of 3 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.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.9.0) reached the registry yesterday.
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.
In the same category: Spec Driven Development, Remote Desktop Commander, Foliosio
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Read your support inbox, tag conversations and save draft replies from your AI agent. Never sends.
No README found in the repo