Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "plainrouter": {
      "type": "http",
      "url": "https://plainrouter.com/mcp"
    }
  }
}

claude mcp add --transport http plainrouter https://plainrouter.com/mcp

[mcp_servers.plainrouter]
url = "https://plainrouter.com/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "plainrouter": {
      "type": "remote",
      "url": "https://plainrouter.com/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "plainrouter": {
      "type": "http",
      "url": "https://plainrouter.com/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=plainrouter&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vcGxhaW5yb3V0ZXIuY29tL21jcCJ9"
}

{
  "servers": {
    "plainrouter": {
      "type": "http",
      "url": "https://plainrouter.com/mcp"
    }
  }
}

{
  "mcpServers": {
    "plainrouter": {
      "httpUrl": "https://plainrouter.com/mcp"
    }
  }
}

extensions:
  "plainrouter":
    enabled: true
    name: "plainrouter"
    type: streamable_http
    uri: "https://plainrouter.com/mcp"
    timeout: 300

Quality 76 / 100good

protocol88 · weight 25

pass
protocol.modernsupports 2026-07-28 (server/discover)
pass
protocol.statelessanswers without a session
pass
protocol.transportstreamable HTTP
warn
protocol.list_ttltools/list declares ttlMs 0, so clients re-fetch it on every use

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene93 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations52 of 52 tools declare readOnlyHint or destructiveHint
pass
tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
warn
tools.token_costabout 18,150 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability25 · weight 15

warn
stability.changes194 tool changes in 30 days
fail
stability.rug_pull12 tools kept their name but changed most of their description in 30 days; review before trusting them

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

52 tools, about 18,150 tokens to load them all · tool set bf1d5f380c1e · tools last changed 2026-10-20 · checked 2026-10-20 15:57 UTC

Tool changes

2026-10-20get_signal_qualityadded
Read stored conversion delivery outcomes, delivery gaps, retained identity presence, and journey coverage for an authorized workspace. The response uses stored data only and does not call advertising APIs.
2026-10-19get_cac_by_channeladded
Read stored ad spend and PlainRouter-earned conversions by channel, with cost per earned conversion by currency. Meta claims are shown separately from earned conversions. Spend and conversion dates are aligned; touch time does not move spend between days.
2026-10-18get_conversion_journeysadded
Read credited conversion journeys for an authorized workspace. Earned is counted by PlainRouter from its own journeys; claimed is reported by Meta. The two are shown side by side and are never reconciled. The output carries no PlainRouter person or visitor identifiers. UTM labels and ad ids appear exactly as the merchant's links sent them.
2026-10-18actions.tests.createchangeddescription, input schema, output schema
before
Create a judging-only Test from 2 to 4 ads in one mirrored Meta ad set. It records a PlainRouter verdict and never creates a proposal or writes to Meta.
after · 79% of words in common
Create a judging-only Test from 2 to 4 ads in one mirrored Meta ad set. Omit the conversion choice to freeze the workspace default. It records a PlainRouter verdict and never creates a proposal or writes to Meta.
2026-10-18actions.tests.showchangeddescription, output schema
before
Read one Test, its stored verdict facts, and loser pause candidate status and reason. Spend per recorded conversion compares variants only within this Test.
after · 92% of words in common
Read one Test, its frozen conversion definition, stored verdict facts, and loser pause candidate status and reason. Spend per recorded conversion compares variants only within this Test.
2026-10-18actions.tests.listchangeddescription, output schema
before
List judging Tests, loser pause candidate status and reason, and observed conversion event choices for the authorized workspace and ad account. Results rank variants only within each Test.
after · 87% of words in common
List judging Tests with their frozen conversion definitions, loser pause candidate status and reason, and observed conversion event choices for the authorized workspace and ad account. Results rank variants only within each Test.
2026-10-18get_arrivals_comparisonchangeddescription
before
Return counted arrivals beside Meta outbound clicks for the authorized workspace and selected trailing window. The purchases block shows Meta-reported Purchase counts under the account attribution setting beside Plainrouter accepted server-side Purchase counts, with its completed account-local window end date and no purchase gap or status. Days before 2026-06-29, or not re-read by the daily sync since 2026-09-27, may still hold Meta link clicks or all clicks.
after · 82% of words in common
Return counted arrivals beside Meta outbound clicks for the authorized workspace and selected trailing window. The conversions block counts retained logical events under the current workspace conversion choices and publishes its selection version, completed local-day period, and availability. The purchases block shows Meta-reported Purchase counts under the account attribution setting beside Plainrouter accepted server-side Purchase counts, with its completed account-local window end date and no purchase gap or status. Days before 2026-06-29, or not re-read by the daily sync since 2026-09-27, may still hold Meta link clicks or all clicks.
2026-10-15launch.plans.listchangedinput schema
2026-10-15launch.creatives.indexchangedinput schema
2026-10-15actions.tests.listchangedinput schema

Showing the latest 10. 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.

Trust 82 / 100

no-repository

provenance55

liveness99

freshness100

hygiene80

+dns-namespace +website +reachable +uptime-97% +updated-19d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://plainrouter.com/mcp` streamable-http	none	yes	97%	697 ms	2026-07-28	2026-10-20
`https://plainrouter.com/mcp/sandbox` streamable-http	none	yes	96%	686 ms	2026-07-28	2026-10-20

Tools (52)

`actions.rules.create`destructive	Store a performance rule disabled. Enabling requires an explicit update; this never evaluates or proposes actions.
`actions.rules.list`read-only	List stored performance rules available to this workspace key. This does not evaluate them.
`actions.rules.show`read-only	Read a stored performance rule and its immutable revisions, with author type only.
`actions.rules.update`destructive	Edit a stored performance rule by appending a revision, or explicitly enable or disable it. This never evaluates or proposes actions.
`actions.tests.create`destructive	Create a judging-only Test from 2 to 4 ads in one mirrored Meta ad set. Omit the conversion choice to freeze the workspace default. It records a PlainRouter verdict and never creates a proposal or writes to Meta.
`actions.tests.list`read-only	List judging Tests with their frozen conversion definitions, loser pause candidate status and reason, and observed conversion event choices for the authorized workspace and ad account. Results rank variants only within each Test.
`actions.tests.show`read-only	Read one Test, its frozen conversion definition, stored verdict facts, and loser pause candidate status and reason. Spend per recorded conversion compares variants only within this Test.
`dry_run_actions`read-only	Preview policy decisions and execution diffs for a proposed Action batch without writing it.
`duplicate-ad-with-creative`destructive	Submit a canonical proposal to duplicate a source Meta ad with a different creative asset. In Ask mode every change waits for your approval; in Full mode, changes that pass admission and workspace policy run automatically. Policy-allowed copies are always created PAUSED.
`get_account_inventory`read-only	Read the authorized workspace account inventory from the Meta mirror, with optional level, status, parent, and ID cursor filters.
`get_account_state`read-only	Return the authorized advertising account, workspace, connection, Signal destination, and currently available account capabilities. This read-only inspection tool does not change the account.
`get_action`read-only	Get one proposed action for the authorized workspace and advertising account. counted_evidence contains frozen target figures and coverage captured at proposal time; null means not captured. The figures inform and never gate.
`get_action_batch`read-only	Get a proposed action batch for the authorized workspace and advertising account. Each action’s counted_evidence contains frozen proposal-time target figures and coverage; null means not captured.
`get_action_decision_receipt`read-only	Get the persisted decision receipt for an authorized proposed action. Version 3 receipts include counted_evidence frozen at proposal time with account-currency values, coverage and the other-currency exclusion. Existing receipts are unchanged.
`get_action_policy`read-only	Get the effective Actions policy for the authorized workspace without creating a policy row.
`get_arrivals_comparison`read-only	Return counted arrivals beside Meta outbound clicks for the authorized workspace and selected trailing window. The conversions block counts retained logical events under the current workspace conversion choices and publishes its selection version, completed local-day period, and availability. The purchases block shows Meta-reported Purchase counts under the account attribution setting beside Plainrouter accepted server-side Purchase counts, with its completed account-local window end date and no purchase gap or status. Days before 2026-06-29, or not re-read by the daily sync since 2026-09-27, may still hold Meta link clicks or all clicks.
`get_cac_by_channel`read-only	Read stored ad spend and PlainRouter-earned conversions by channel, with cost per earned conversion by currency. Meta claims are shown separately from earned conversions. Spend and conversion dates are aligned; touch time does not move spend between days.
`get_consent_rates`read-only	Read recorded consent rates and recent consent receipts for the requested authorized workspace. Rates cover the retained period and split Analytics and Marketing grants by day, country, language, and banner version. This tool does not change data or call advertising APIs.
`get_conversion_journeys`read-only	Read credited conversion journeys for an authorized workspace. Earned is counted by PlainRouter from its own journeys; claimed is reported by Meta. The two are shown side by side and are never reconciled. The output carries no PlainRouter person or visitor identifiers. UTM labels and ad ids appear exactly as the merchant's links sent them.
`get_cookie_scan`read-only	Read the latest pre-consent cookie scan for the authorized workspace. Blocked and failed scans report findings as unavailable, never as a clean result. When bot protection blocks the start page, allowlist the PlainRouterScanner user agent before retrying.
`get-creative-library`read-only	Return Meta image and video assets with the ads and last-30-day performance historically associated with each asset.
`get_install_instructions`read-only	Return managed-hostname Path A installation material and first-arrival state for the authorized workspace. Returns no same-origin forwarding material.
`get_inventory_metrics`read-only	Read daily Meta metrics beside counted PlainRouter arrivals for mirrored campaigns, ad sets and ads. object_metrics contains account-timezone daily comparisons; unmatched_arrivals is one workspace/window count without unknown IDs. Counts are null when the arrivals store is disabled. Optional change history is retention-clamped.
`get_performance`read-only	Admissible proposal evidence: reconciliation meta_reported is the existing Meta-reported conversions count compared with gateway_verified accepted conversions. The separate purchases block shows Meta-reported Purchase counts under the account attribution setting beside Plainrouter accepted server-side Purchase counts, with its completed account-local window start and end dates and no purchase gap or status. Includes stored daily Meta spend and delivery metrics. platform_claimed_clicks means Meta outbound clicks. Days before 2026-06-29, or not re-read by the daily sync since 2026-09-27, may still hold Meta link clicks or all clicks.
`get_render`read-only	Inspect a workspace render and its draft output creative ids.
`get_signal_health`read-only	Diagnostic view of first-party event flow, Meta delivery outcomes, match quality, and reconciliation gaps from Plainrouter stored measurements. Not admissible evidence for spend-affecting proposals. Does not call the Marketing API.
`get_signal_quality`read-only	Read stored conversion delivery outcomes, delivery gaps, retained identity presence, and journey coverage for an authorized workspace. The response uses stored data only and does not call advertising APIs.
`launch.creatives.index`read-only	List creatives in the workspace bound to the authenticated execution token.
`launch.creatives.show`read-only	Show one creative in the workspace bound to the authenticated execution token.
`launch.creatives.status`destructive	Set the status of one creative in the workspace bound to the authenticated execution token.
`launch.creatives.store`destructive	Store one JPEG, PNG, MP4, or QuickTime creative from strict base64 content in the token-bound workspace. When supplying output from an outside tool, set tags.generator, tags.generator_job and, for a variation, tags.parent_creative. PlainRouter’s own creative tools will set these tags on every creative they make; images enter the library by upload or launch.creatives.store-from-url.
`launch.creatives.store-from-url`destructive	Fetch and store one creative from a vetted HTTPS URL in the token-bound workspace. When supplying output from an outside tool, set tags.generator, tags.generator_job and, for a variation, tags.parent_creative. PlainRouter’s own creative tools will set these tags on every creative they make; images enter the library by upload or launch.creatives.store-from-url.
`launch.plans.copy`destructive	Copy a failed plan to a new draft with the same content. Validate and submit the draft afresh; the failed plan and its history stay unchanged.
`launch.plans.create`destructive	Create a deployment plan for the approved ad account.
`launch.plans.execute`destructive	Execute one deployment plan in the workspace and ad account bound to the execution token; requires the review_version returned by the plan read you acted on. Changed plans are refused before any intent or staging; identical intent_key and review_version retries replay. All provider mutations are proposed through Actions.
`launch.plans.list`read-only	List deployment plans for the approved ad account, including each current review_version to pass when executing the reviewed plan.
`launch.plans.show`read-only	Read one deployment plan and its current review_version and latest launch-intent status in the workspace and ad account bound to the execution token.
`launch.plans.update`destructive	Update a deployment plan for the approved ad account.
`launch.plans.validate`destructive	Validate a deployment plan for the approved ad account.
`list_actions`read-only	List proposed actions for the authorized workspace and advertising account.
`list_creatives`read-only	List workspace creative metadata and Library provenance. Images are available only through preview_creatives.
`list_templates`read-only	List the available versioned ad templates, usage descriptions, the default choice, copy slots and supported sizes.
`list_workspaces`read-only	List the workspaces and effective access tiers in this credential scope.
`preview_creatives`destructive	Show workspace creatives to a person in the Creative Preview app. Missing derivatives return pending and queue a bounded build. Originals and image bytes are never returned.
`propose-actions`destructive	Propose a batch of budget, status, upload, or creative-duplication actions for the approved ad account. In Ask, every policy-allowed change waits for a person to approve it. In Full, policy-allowed changes run automatically. Rule violations are blocked and shown in the Inbox, and cannot be approved. The execution kill switch stops further writes and never undoes a landed change. Dispatch still requires a live grant, an account in the workspace, and no duplicate write. Legacy set_status and adjust_budget never run. Meta target proposals freeze counted_evidence over the last seven completed account-local days for display only. Evidence may cite get_inventory_metrics leaf fields for the proposed target: Meta inline link clicks, counted arrivals and Purchase count/value at that target’s own level. Spend, impressions, child-object rows, containers, ratios and other action types are refused.
`render_ad`destructive	Render ad copy over an image already in the workspace library using a template id and version, selected sizes, and a required request_key.
`resume_render`destructive	Inspect a workspace render and resume only a held run. Running states return inspect guidance.
`revoke_grant`destructive	Revoke an active workspace grant. The caller must hold the revoke_grant scope in the same workspace or be the human delegator of the granted agent.
`submit_feedback`destructive	Report a bug or a missing capability you hit while using this server. Say what you were trying to do and what happened. Nothing in the account changes and no reply is sent here.
`upload-asset`destructive	Stage a JPEG/PNG image and submit a canonical upload action through workspace policy. In Ask mode every change waits for your approval; in Full mode, changes that pass admission and workspace policy run automatically.
`validate_sandbox_event`read-only	Validate a synthetic, identity-free conversion event against the Plainrouter schema. Requires no account, API key, or OAuth flow. Nothing is stored and nothing is sent to an advertising provider. Use this to confirm the server is reachable and that an event payload is well formed before requesting credentials.
`verify_signal_ingestion`destructive	Verify server-side Signal ingestion by writing one idempotent, identity-free modeled event for the authorized workspace. This confirms ledger receipt but does not count as real arrival evidence or complete onboarding. No spend capability.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "com.plainrouter/mcp",
  "_meta": {
    "io.modelcontextprotocol.registry/publisher-provided": {
      "capabilities": {
        "io.modelcontextprotocol/ui": {}
      },
      "serverCardUrl": "https://plainrouter.com/.well-known/mcp.json"
    }
  },
  "title": "Plainrouter",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://plainrouter.com/mcp",
      "type": "streamable-http"
    },
    {
      "url": "https://plainrouter.com/mcp/sandbox",
      "type": "streamable-http"
    }
  ],
  "version": "0.4.1",
  "websiteUrl": "https://plainrouter.com",
  "description": "Meta Ads MCP: read ad accounts and signal health; propose governed changes under Ask or Full."
}