Search / com.spillmark/spillmark
protogridR0· no sign-inRead-only Amazon profit, fee, ACoS, and geo-holdout MCP tools for Claude, ChatGPT, and agents.
v1.0.1 · active · repository · website · descriptor JSON · versions
{
"mcpServers": {
"spillmark": {
"type": "http",
"url": "https://spillmark.com/mcp",
"headers": {
"Authorization": "Bearer ${SPILLMARK_TOKEN}"
}
}
}
}claude mcp add --transport http spillmark https://spillmark.com/mcp --header "Authorization: Bearer ${SPILLMARK_TOKEN}"[mcp_servers.spillmark]
url = "https://spillmark.com/mcp"
bearer_token_env_var = "SPILLMARK_TOKEN"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"spillmark": {
"type": "remote",
"url": "https://spillmark.com/mcp",
"enabled": true,
"headers": {
"Authorization": "Bearer {env:SPILLMARK_TOKEN}"
}
}
}
}{
"mcpServers": {
"spillmark": {
"type": "http",
"url": "https://spillmark.com/mcp",
"headers": {
"Authorization": "Bearer ${SPILLMARK_TOKEN}"
}
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=spillmark&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vc3BpbGxtYXJrLmNvbS9tY3AiLCJoZWFkZXJzIjp7IkF1dGhvcml6YXRpb24iOiJCZWFyZXIgJHtTUElMTE1BUktfVE9LRU59In19"
}{
"servers": {
"spillmark": {
"type": "http",
"url": "https://spillmark.com/mcp",
"headers": {
"Authorization": "Bearer ${SPILLMARK_TOKEN}"
}
}
}
}{
"mcpServers": {
"spillmark": {
"httpUrl": "https://spillmark.com/mcp",
"headers": {
"Authorization": "Bearer ${SPILLMARK_TOKEN}"
}
}
}
}extensions:
"spillmark":
enabled: true
name: "spillmark"
type: streamable_http
uri: "https://spillmark.com/mcp"
headers:
"Authorization": "Bearer ${SPILLMARK_TOKEN}"
timeout: 300
Placeholders to fill from your own secret store: ${SPILLMARK_TOKEN}. The registry never accepts secret values.
protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28protocol.statelessonly applies to 2026-07-28 serversprotocol.transportstreamable HTTPprotocol.list_ttlonly applies to 2026-07-28 serversauth.prm, auth.as_metadata, auth.cimdno remote uses OAuthauth.secret_in_urlno templated URLtools.descriptionsevery tool has a descriptiontools.description_lengthdescriptions are concisetools.schemasevery tool has an object input schematools.annotations3 of 3 tools declare readOnlyHint or destructiveHinttools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: list_calculators (destructiveHint, idempotentHint); how_lift_is_calculated (destructiveHint, idempotentHint); run_calculator (destructiveHint, idempotentHint)tools.token_costabout 485 tokens to load every tooltools.api_dumptools are not a one-to-one API dumpstability.changes1 tool changes in 30 daysstability.rug_pullno tool changed its meaning under the same namedeps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI packagelist_calculatorschangeddescriptionSpillmark's free Amazon and Meta ads calculators (holdout test size, incremental ROAS, break-even ROAS, ACoS, TACoS, Amazon fees and profit, LTV and CAC), with each one's inputs and example values. Use run_calculator to run one.
Spillmark's free Amazon and Meta ads calculators (holdout test size, brand-size MDE, geo holdout states, ad waste, Meta ROAS reality check, incremental ROAS, break-even ROAS, ACoS, TACoS, Amazon fees and profit, LTV and CAC), with each one's inputs and example values. Use run_calculator to run one.
Full history: list_changes · trend: quality JSON.
Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.
+repository +dns-namespace +website +reachable +uptime-100% +updated-1d-ago
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
| remote | auth | reachable | uptime 30d | p50 | protocol | last ok |
|---|---|---|---|---|---|---|
https://spillmark.com/mcp streamable-http | none | yes | 100% | 491 ms | 2025-11-25 | 2026-11-07 |
how_lift_is_calculatedread-only | Spillmark's method in brief: how a geo holdout test measures the sales Meta ads cause on Amazon, with links to the full method and a sample report on made-up numbers. |
list_calculatorsread-only | Spillmark's free Amazon and Meta ads calculators (holdout test size, brand-size MDE, geo holdout states, ad waste, Meta ROAS reality check, incremental ROAS, break-even ROAS, ACoS, TACoS, Amazon fees and profit, LTV and CAC), with each one's inputs and example values. Use run_calculator to run one. |
run_calculatorread-only | Runs one calculator from list_calculators on your numbers and returns the headline result, the supporting figures, a one-sentence reading, and a link that opens the calculator with the same inputs. Missing inputs use the calculator's example values. Enter percents as points (15 means 15%), choices as the option index. |
Schemas: list_tools.
{
"name": "com.spillmark/spillmark",
"icons": [
{
"src": "https://spillmark.com/icon",
"sizes": [
"48x48"
],
"mimeType": "image/png"
}
],
"title": "Spillmark",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"remotes": [
{
"url": "https://spillmark.com/mcp",
"type": "streamable-http",
"headers": [
{
"name": "Authorization",
"isSecret": true,
"description": "Optional. 'Bearer sm_...' from Settings -> Agent access, for a brand's own profit and incrementality record. Public tools need no key."
}
]
}
],
"version": "1.0.1",
"repository": {
"url": "https://github.com/burmanharry/spillmark-mcp",
"source": "github"
},
"websiteUrl": "https://spillmark.com/uses/amazon-ads-mcp",
"description": "Read-only Amazon profit, fee, ACoS, and geo-holdout MCP tools for Claude, ChatGPT, and agents."
}