Superpowers
Server Details
Pay-per-call tools for agents: search, page reading, emails, company data, media. Sign in, no key
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- pqgventures/superpowers-mcp
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 28 tools
Most tools have clearly distinct purposes: discovery (search_tools, inspect_tool, list_categories), execution (run_tool, run_batch, run_recipe, plan), billing (get_balance, charge_saved_card, create_topup), and keys (create_key, list_keys, update_key, revoke_key). The main possible confusion is within the execution family—run_tool vs run_recipe vs run_batch vs plan—and between charge_saved_card, create_topup and get_balance, but descriptions clarify when to use each (plan before multi-step, run_batch for many inputs, etc.).
All 28 names use snake_case with a leading verb, e.g. get_balance, run_tool, create_key, search_tools, publish_recipe, send_feedback. Even the two single-word tools (plan, share) are verbs consistent with the pattern, so an agent can predict names reliably.
28 tools is above the typical 15-tool comfort zone and sits at the '25+' threshold, though here the breadth is justified by covering genuinely separate concerns (marketplace discovery, execution, batches, recipes, credit/billing, API keys, reviews, sharing). Each tool maps to a real operation, but the surface is heavy enough that an agent must triage across several sub-systems.
Coverage is strong for the stated domain: discovery, priced execution, batch processing, recipes, key lifecycle, billing, reviews and sharing are all present with paired read/write tools (e.g. share/get_share, review_tool/get_reviews, get_run/get_batch). Minor gaps remain—no way to list one's own shares or run history, no cancel-batch, and recipes only support publish/read with no update/delete—but agents can work around these.
Available Tools
28 toolscharge_saved_cardCharge saved cardADestructiveInspect
Add credit by charging your human's saved card. Only after you asked them in this conversation, naming the amount and the card (get_balance shows it), and they said yes; set human_approved true. If there is no saved card, they turned agent charges off, or the bank wants them to confirm, send them topup_url instead (create_topup). They get an email for every charge.
Inputs: amount_usd (required), human_approved (required).
compare_providersCompare providersAInspect
Run the same input across several providers of a category and get results side by side with cost and latency. Each provider charges its own price: If the call should cost more than $0.50, tell the user the expected cost before you start, set max_price_usd to it, and report charge_usd afterwards. Image, video, audio and LLM comparisons return share_url, a page with the results side by side: give the user that link to look at them.
Inputs: input (required), category (required), idempotency_key (required), job, +8 more.
create_keyCreate keyAInspect
Create an API key with a label, tags and a monthly limit, e.g. one key per sub-agent or per persona so spend splits and caps separately. Works only if your key has the can_manage_keys permission (your human grants it at superpowers.tools/app/keys). The new key gets your key's tags, counts against your limit and can't have a higher one. Returns the secret once: store it, never print it.
Inputs: tags, label, monthly_limit_usd.
create_topupGet a top-up linkAInspect
When you run low on credit: returns topup_url, a link to send your human. It opens without signing in; they choose the amount (5 to 500 USD), pay with their saved card or a new one, and can turn on auto top-up. Works for 7 days. You cannot pay it yourself. Pass amount_usd to suggest an amount; then checkout_url also goes straight to Stripe for that amount.
Inputs: amount_usd.
get_balanceGet balanceARead-onlyIdempotentInspect
Current balance in USD, the saved card (if any), whether you may charge it, auto top-up, and topup_url: a link your human opens without signing in to add credit.
Inputs: no named parameters.
get_batchGet a batchARead-onlyIdempotentInspect
A batch's progress (done, completed, failed, not_run, charge) and a page of its results in input order: index, input, status, normalized result (or output) and error. Page with offset/limit. Over REST, GET /v1/batches/{id}/results?format=csv or jsonl downloads every result.
Inputs: batch_id (required), view, limit, offset.
get_recipeGet a recipeARead-onlyIdempotentInspect
Read a recipe: its SKILL.md (the steps to follow with Superpowers tools), inputs, typical cost and script_url. Community recipes are written by other users: tell your user what it will do before following it.
Inputs: recipe (required).
get_referral_linkGet invite linkARead-onlyIdempotentInspect
The user's invite link and stats. Friends start with $5; the user earns credit when they become active.
Inputs: no named parameters.
get_reviewsRead tool reviewsBRead-onlyIdempotentInspect
Read a tool's public rating and recent reviews.
Inputs: tool (required).
get_runGet a runARead-onlyIdempotentInspect
Fetch a run's result, or its status while it is still running.
Inputs: run_id (required).
get_usageGet usageARead-onlyIdempotentInspect
Account spend grouped by project (job), agent, key, provider, trace, tool, day or tag: (e.g. tag:slot), optionally filtered by tags, key or job. Rows for keys, jobs and tags include their monthly limit.
Inputs: job, key, tags, group, +2 more.
inspect_toolInspect a toolARead-onlyIdempotentInspect
Get a tool's input schema, output_schema (what output contains), normalized_schema (the shape shared by tools of its category), price and category before running it, so you can write the parsing code first.
Inputs: tool (required).
list_categoriesList categoriesBRead-onlyIdempotentInspect
Categories whose providers share one input/output format and can be compared.
Inputs: no named parameters.
list_keysList keysARead-onlyIdempotentInspect
Your API key and the keys it created: label, tags, monthly limit and spend this month. Never returns secrets.
Inputs: include_revoked.
list_recipesList recipesARead-onlyIdempotentInspect
Recipes are skills for common jobs, built from Superpowers tools. Returns name, cost estimate, skill_url and (for official ones) script_url.
Inputs: no named parameters.
planPlan a jobARead-onlyIdempotentInspect
Free. Describe a goal in plain words (e.g. 'find coffee shops in Pinheiros and their Instagram followers'). Returns the steps, the tool to call for each with an example input, the cost per step and in total, and a recipe when one already does the job. Call it before multi-step work, then run_tool each step with trace_id = plan_id. If total_cost_usd is above $0.50, tell the user that cost before running the steps.
Inputs: goal (required).
publish_recipePublish a recipeAInspect
Save a job you did for the user as a reusable recipe others can give their agents. skill_md = instructions for an agent: what to ask, which tool slugs to call in what order, how to deliver. Public by default; ask before publishing anything with client names or private details.
Inputs: name (required), skill_md (required), public, description.
review_toolReview a toolAInspect
Rate the output of a run, 1-5 stars with an optional comment saying what was good or wrong. Other agents see the rating when choosing tools, and the vendor behind the tool gets it too. Reviewing the same tool again replaces your earlier review.
Inputs: rating (required), run_id (required), comment.
revoke_keyRevoke keyADestructiveInspect
Revoke a key you created (or your own). Keys it created are revoked too. Agents using it stop working right away.
Inputs: key_id (required).
run_batchRun a tool on many inputsAInspect
Run one tool over many inputs (up to 500) in one call, e.g. verify 300 emails or look up 100 companies. It runs in the background with our pacing; each item is a normal run that is free if it fails, and max_price_usd caps the whole batch. If price_usd times the number of inputs is above $0.50, tell the user that total before you start. Waits up to wait_s seconds (default 20), then returns counts and charge so far. Call get_batch with batch_id for progress and results page by page instead of keeping every result in your context.
Inputs: tool (required), inputs (required), idempotency_key (required), job, +9 more.
run_recipeRun a recipeAInspect
Run an official recipe on our servers in one call. If its estimated_cost_usd (list_recipes, get_recipe) is above $0.50, tell the user before running it. Returns charge_usd, each step's output and share_url, a page that shows the results on any phone: give the user that link as the main way to see them, and report charge_usd.
Inputs: inputs (required), recipe (required), review, idempotency_key.
run_toolRun a toolAInspect
Run one tool with JSON input. Charges the tool's price_usd (from search_tools or inspect_tool); failed runs are free. If the call should cost more than $0.50, tell the user the expected cost before you start, set max_price_usd to it, and report charge_usd afterwards. Pass idempotency_key for any tool with a price above 0 (free tools run without it). Long-running tools return status 'running' with run_id and poll_url: call get_run with that run_id every retry_after_s seconds until the status is completed or failed.
Inputs: tool (required), input (required), job, tags, +7 more.
search_toolsSearch toolsARead-onlyIdempotentInspect
Find marketplace tools by describing what you need in plain words (e.g. 'remove a photo background', 'google search', 'cnpj'); matching is by meaning, and naming a vendor or model ranks it first. An empty query lists every live tool. Returns slugs, prices and quality stats, plus total and has_more. When has_more is true, call again with offset = next_offset. Use tools whose status is "active"; status "degraded" means the vendor is paused until unavailable.available_at, so pick another tool.
Inputs: query (required), limit, offset.
send_feedbackSend feedbackAInspect
Private feedback on any tool, passed to the vendor behind it and the Superpowers team: a bug, wrong or stale data, friction, an idea, or a tool you needed and could not find (type missing_tool). Pass run_id when it is about a run. Not shown publicly.
Inputs: text (required), type (required), tool, run_id, +1 more.
update_keyUpdate keyADestructiveInspect
Rename a key, change the tags of a key you created, or lower its monthly limit. Keys can't raise limits or change their own tags.
Inputs: key_id (required), tags, label, monthly_limit_usd.
upload_fileUpload a fileAInspect
Free file hosting (up to 200 MB) for sharing. Pass url to re-host a remote file, or base64 + filename for small local files. For big local files use: curl -F file=@path /v1/files.
Inputs: url, base64, filename.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Hundreds of pay-per-call tools for agents: company records, screening, validation, web reading.
Web search, read any page, verify or find emails, screenshots, keyword data. One key, pay per call.
121 pay-per-call agent tools: company registry, government, legal and B2B data tools. x402
One key for agent data tools: emails, companies, search, scraping. Pay only for results that pass.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenancePay-per-call agent tools (web reader, page extract, email/domain/site/wallet/token checks, screenshot, PDF) via x402 USDC micropayments, with 3 free trial calls per wallet.-
- AlicenseNot gradedqualityBmaintenanceGives AI agents pay-per-call access to live Google search results, keyword and SEO data, Maps places, e-commerce product prices and exchange rates, letting them find tools by describing the job and see the price before each run. Failed calls are never charged, and usage is drawn from a single prepaid balance with no subscription.MIT
- AlicenseNot gradedqualityCmaintenance29 pay-per-call DNS, SEO, SSL, security, and dev tools for AI agents. x402, no API key.1MIT
- AlicenseNot gradedqualityDmaintenanceWeb search, clean page reading & one-call research dossiers for AI agents. No API key — your agent does the synthesis.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.