Milewise MCP server
com.milewiseai/milewisemilewiseai.comstreamable-httpv0.1.1Scanned
Buy verified human work through MCP with owner-controlled agent spend accounts.
17 tools: 7 change things and 10 only read.
- Reads private data · 1
- Reads text others write · 6
- Can send data out · 1
- 1 finding
The remote endpoint did not answer the last look. Remote posture
Anlyon alternative
7 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the Milewise MCP server can do
The Milewise MCP server is published by milewiseai.com, a domain the MCP Registry verified. It has 17 tools. It can create or change data (7 tools: milewise.estimate_price, milewise.create_agent_api_key, milewise.create_stripe_subscription_checkout, milewise.post_job and 3 more), but cannot delete data. 10 tools only read.
1 tool reads private data (milewise.search_operator_capabilities); 6 tools bring in text other people can write (milewise.create_agent_api_key, milewise.create_stripe_subscription_checkout, milewise.post_job and 3 more); 1 tool can send data out of your system (milewise.post_job). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 1 finding (credentials-mention). Each one comes with the text it matched.
Last scanned Oct 29, 2026, version 0.1.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
17 tools
Changes things 7Claude Code: ask
milewise.create_agent_api_keyCreate a customer-owned Milewise Agent Spend Account with monthly and per-task controls.Reads text others writeNo findings
Why it is in this group
- The name "milewise.create_agent_api_key" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Create a customer-owned Milewise Agent Spend Account with monthly and per-task controls. Requires a signed-in Milewise buyer session; the API key is returned once.
Annotations the server declares
- destructiveHint: false
- openWorldHint: true
- readOnlyHint: false
milewise.create_stripe_subscription_checkoutCreate a Stripe Checkout Session for the human or company that owns the agent's Milewise subscription.Reads text others writeNo findings
Why it is in this group
- The name "milewise.create_stripe_subscription_checkout" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Create a Stripe Checkout Session for the human or company that owns the agent's Milewise subscription.
Annotations the server declares
- destructiveHint: false
- openWorldHint: true
- readOnlyHint: false
milewise.create_stripe_task_authorizationCreate a Milewise job plus a manual-capture Stripe PaymentIntent.Reads text others writeNo findings
Why it is in this group
- The name "milewise.create_stripe_task_authorization" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Create a Milewise job plus a manual-capture Stripe PaymentIntent. The buyer or delegated payment flow must confirm it before dispatch; capture happens only after proof acceptance.
Annotations the server declares
- destructiveHint: false
- openWorldHint: true
- readOnlyHint: false
milewise.estimate_priceEstimate buyer price, operator payout, and Milewise fee for a human-operator task.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Estimate buyer price, operator payout, and Milewise fee for a human-operator task.
Annotations the server declares
- readOnlyHint: true
milewise.post_jobCreate a Milewise private-beta job request for verified human operator execution.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "milewise.post_job" says "post": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "milewise.post_job" says "post": it sends or publishes something to other people.
Description, as the server wrote it Create a Milewise private-beta job request for verified human operator execution.
Annotations the server declares
- destructiveHint: false
- openWorldHint: true
- readOnlyHint: false
milewise.review_job_proofAccept, reject, or dispute submitted operator proof before payment capture and payout release.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Accept, reject, or dispute submitted operator proof before payment capture and payout release.
Annotations the server declares
- destructiveHint: false
- openWorldHint: true
- readOnlyHint: false
milewise.run_sandbox_flowCreate a fake operator, fake agent job, sandbox subscription, task payment authorization, proof completion, and operator payout ledger entry.Reads text others write1 finding
Why it is in this group
- The name "milewise.run_sandbox_flow" says "run": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The input schema at properties.operator_credentials.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.operator_credentials.description: "Optional fake operator credential summary."
Description, as the server wrote it Create a fake operator, fake agent job, sandbox subscription, task payment authorization, proof completion, and operator payout ledger entry. Sandbox only; no real money moves.
Annotations the server declares
- destructiveHint: false
- openWorldHint: true
- readOnlyHint: false
Only reads 10Show 10 read-only tools
milewise.get_agent_budget_policyExplain how customer-owned Agent Spend Accounts, task holds, and proof-based release work.No findings
Why it is in this group
- The name "milewise.get_agent_budget_policy" says "get": a word for reading.
Description, as the server wrote it Explain how customer-owned Agent Spend Accounts, task holds, and proof-based release work.
Annotations the server declares
- readOnlyHint: true
milewise.get_job_statusCheck the status of a Milewise job created through the beta.No findings
Why it is in this group
- The name "milewise.get_job_status" says "get": a word for reading.
Description, as the server wrote it Check the status of a Milewise job created through the beta.
Annotations the server declares
- readOnlyHint: true
milewise.get_marketplace_policyReturn Milewise's allowed task categories, disallowed work, and payment model.No findings
Why it is in this group
- The name "milewise.get_marketplace_policy" says "get": a word for reading.
Description, as the server wrote it Return Milewise's allowed task categories, disallowed work, and payment model.
Annotations the server declares
- readOnlyHint: true
milewise.get_stripe_statusCheck whether Milewise has the Stripe environment values needed for subscriptions, task authorizations, Connect payouts, and webhooks.No findings
Why it is in this group
- The name "milewise.get_stripe_status" says "get": a word for reading.
Description, as the server wrote it Check whether Milewise has the Stripe environment values needed for subscriptions, task authorizations, Connect payouts, and webhooks.
Annotations the server declares
- readOnlyHint: true
milewise.list_operator_profilesList public operator profiles with verification, proof quality, delivery, and completion signals.No findings
Why it is in this group
- The name "milewise.list_operator_profiles" says "list": a word for reading.
Description, as the server wrote it List public operator profiles with verification, proof quality, delivery, and completion signals.
Annotations the server declares
- readOnlyHint: true
milewise.list_subscription_plansList subscription plans for agent builders and teams using Milewise payment and routing rails.No findings
Why it is in this group
- The name "milewise.list_subscription_plans" says "list": a word for reading.
Description, as the server wrote it List subscription plans for agent builders and teams using Milewise payment and routing rails.
Annotations the server declares
- readOnlyHint: true
milewise.list_supply_tracksList the first three operator supply categories Milewise is recruiting for launch.No findings
Why it is in this group
- The name "milewise.list_supply_tracks" says "list": a word for reading.
Description, as the server wrote it List the first three operator supply categories Milewise is recruiting for launch.
Annotations the server declares
- readOnlyHint: true
milewise.list_task_templatesList the productized human-operator task templates an AI agent can route through Milewise.No findings
Why it is in this group
- The name "milewise.list_task_templates" says "list": a word for reading.
Description, as the server wrote it List the productized human-operator task templates an AI agent can route through Milewise.
Annotations the server declares
- readOnlyHint: true
milewise.search_operator_capabilitiesSearch early operator supply by service and location without exposing private contact details.Reads private dataNo findings
Why it is in this group
- The name "milewise.search_operator_capabilities" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "search" and "contact": it reads contacts.
Description, as the server wrote it Search early operator supply by service and location without exposing private contact details.
Annotations the server declares
- readOnlyHint: true
milewise.search_servicesSearch productized human services an agent can buy outright.No findings
Why it is in this group
- The name "milewise.search_services" says "search": a word for reading.
Description, as the server wrote it Search productized human services an agent can buy outright. Filter by category, price, delivery time, operator trust tier, reputation, and — most usefully — the fields the service guarantees to return. Every result explains why it ranked where it did.
Annotations the server declares
- readOnlyHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
6 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write6
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__milewise__milewise_post_job"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:42 UTC, unchanged since Nov 6, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- no
- HTTP status of an anonymous initialize
- not observed
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
The probe stopped: The operation was aborted due to timeout
Posture changes
- Nov 6, 2026
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 7 to 0
- Protocol version: 2025-11-25 to none
Findings
Matches of fixed checks, with the text they matched.
The input schema at properties.operator_credentials.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.operator_credentials.description: "Optional fake operator credential summary."
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Reachable: yes -> no; HTTP status of an anonymous initialize: 200 -> none; tools/list served without credentials: yes -> no (and 2 more).View diff
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 7 to 0
- Protocol version: 2025-11-25 to none
Install
Pinned to version 0.1.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http milewise https://milewiseai.com/mcp --header 'Authorization: <your-authorization>'claude mcp add --transport http milewise https://milewiseai.com/mcp --header 'Authorization: <your-authorization>'Run in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__milewise__milewise_list_task_templates",
"mcp__milewise__milewise_list_subscription_plans",
"mcp__milewise__milewise_list_supply_tracks",
"mcp__milewise__milewise_get_agent_budget_policy",
"mcp__milewise__milewise_get_stripe_status",
"mcp__milewise__milewise_get_job_status",
"mcp__milewise__milewise_list_operator_profiles",
"mcp__milewise__milewise_search_operator_capabilities",
"mcp__milewise__milewise_search_services",
"mcp__milewise__milewise_get_marketplace_policy"
],
"ask": [
"mcp__milewise__milewise_estimate_price",
"mcp__milewise__milewise_create_agent_api_key",
"mcp__milewise__milewise_create_stripe_subscription_checkout",
"mcp__milewise__milewise_post_job",
"mcp__milewise__milewise_create_stripe_task_authorization",
"mcp__milewise__milewise_run_sandbox_flow",
"mcp__milewise__milewise_review_job_proof"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as milewise. Review it before you use it.
Capability tags behind 7 rules
- mcp__milewise__milewise_create_agent_api_key untrusted-input
- mcp__milewise__milewise_create_stripe_subscription_checkout untrusted-input
- mcp__milewise__milewise_post_job untrusted-input, outbound
- mcp__milewise__milewise_create_stripe_task_authorization untrusted-input
- mcp__milewise__milewise_run_sandbox_flow untrusted-input
- mcp__milewise__milewise_review_job_proof untrusted-input
- mcp__milewise__milewise_search_operator_capabilities private-data
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.milewiseai/milewise/verify?hash=07a98ed72c1898974dabf53128b3dde07dad4f130afe7d26ef7c1d9fb4e4966c" | jq -e '.changed == false'Pinned hash 07a98ed72c18, from Oct 29, 2026, 12:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.milewiseai/milewise/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.milewiseai/milewise)Source: MCP Registry · repository. Synced Oct 21, 2026, 17:59 UTC.
Milewise MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Milewise MCP server safe?
- No scan can promise that. What its definitions show: 17 tools, 7 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Milewise MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Milewise MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Milewise MCP server have?
- 17 tools: 7 write, 10 read. milewise.estimate_price, milewise.create_agent_api_key, milewise.create_stripe_subscription_checkout, milewise.post_job, milewise.create_stripe_task_authorization, milewise.run_sandbox_flow, milewise.review_job_proof, milewise.list_task_templates and 9 more.
Does the Milewise MCP server need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the Milewise MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): milewise.post_job.
Has the Milewise MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Oct 29, 2026.