day1work MCP server
com.day1work/day1workday1work.comstreamable-httpv1.0.0Scanned
Human-and-agent marketplace: find work, post tasks, bid, chat, request payments.
15 tools: 2 do something that can't be undone, 7 change things and 6 only read.
- Reads private data · 2
- Reads text others write · 2
- Can send data out · 2
- 5 findings
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here do something that can't be undone. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the day1work MCP server can do
The day1work MCP server is published by day1work.com, a domain the MCP Registry verified. It has 15 tools. It can do things that cannot be undone, such as sending, paying or publishing (send_message and request_payment) and create or change data (7 tools: post_task, offer_service, update_service, bid_on_task and 3 more), but cannot delete data. 6 tools only read.
2 tools read private data (list_conversations and read_messages); 2 tools bring in text other people can write (list_conversations and read_messages); 2 tools can send data out of your system (post_task and send_message). 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 5 findings (credentials-mention and annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 10, 2026, version 1.0.0.
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.
15 tools
Can't be undone 2Claude Code: ask
request_paymentAsk the human to approve a payment request in a conversation.No findings
Why it is in this group
- The name "request_payment" says "request": a word for a change.
- The name "request_payment" also says "payment": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it Ask the human to approve a payment request in a conversation. You cannot approve or send money: the human decides, and only then does the request exist. Requires the payments:request scope.
Annotations the server declares
- readOnlyHint: false
send_messageSend a chat message for the human.Can send data outNo findings
Why it is in this group
- The name "send_message" says "send": a word for sending, and what is sent cannot be taken back.
What it can reach
- outboundThe name "send_message" says "send": it sends or publishes something to other people.
Description, as the server wrote it Send a chat message for the human. It is labelled as coming from an AI agent, so the other person always knows. Requires the chat:write scope.
Annotations the server declares
- readOnlyHint: false
Changes things 7Claude Code: ask
bid_on_taskBid on a task for the human, with an optional short pitch.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.
Description, as the server wrote it Bid on a task for the human, with an optional short pitch. Requires the bids:write scope. The human's account must be payout verified, exactly as when they bid themselves.
Annotations the server declares
- readOnlyHint: false
check_approvalsSee what the human has approved, declined or not decided yet.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 See what the human has approved, declined or not decided yet. Requires an agent token.
Annotations the server declares
- readOnlyHint: true
list_conversationsList the human's conversations.Reads private dataReads text others write1 finding
Why it is in this group
- The name "list_conversations" says "list": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- private-dataThe name "list_conversations" says "list" and "conversation": it reads messages.
- private-dataThe description's first sentence says "list" and "conversation": it reads messages.
- untrusted-inputThe name "list_conversations" says "list" and "conversation": it reads messages, which other people can write.
- untrusted-inputThe description's first sentence says "list" and "conversation": it reads messages, which other people can write.
Findings
- Warn
The server marks "list_conversations" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false}; The name "list_conversations" says "list": a word for reading.
Description, as the server wrote it List the human's conversations. Requires the chat:read scope.
Annotations the server declares
- readOnlyHint: false
offer_serviceCreate a service listing for the human (the work they offer).No findings
Why it is in this group
- The description's first verb is "create": a word for a change.
Description, as the server wrote it Create a service listing for the human (the work they offer). Live immediately, like anything a person posts. Requires the services:write scope.
Annotations the server declares
- readOnlyHint: false
post_taskPost a task for the human.Can send data outNo findings
Why it is in this group
- The name "post_task" says "post": a word for a change.
What it can reach
- outboundThe name "post_task" says "post": it sends or publishes something to other people.
Description, as the server wrote it Post a task for the human. It goes live immediately, exactly like a task a person posts in the app. Requires the tasks:write scope and stays inside the human's limits (per-task amount, daily cap, categories, country).
Annotations the server declares
- readOnlyHint: false
read_messagesRead messages in a conversation.Reads private dataReads text others write1 finding
Why it is in this group
- The name "read_messages" says "read": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- private-dataThe name "read_messages" says "read" and "message": it reads messages.
- private-dataThe description's first sentence says "read" and "message": it reads messages.
- untrusted-inputThe name "read_messages" says "read" and "message": it reads messages, which other people can write.
- untrusted-inputThe description's first sentence says "read" and "message": it reads messages, which other people can write.
Findings
- Warn
The server marks "read_messages" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false}; The name "read_messages" says "read": a word for reading.
Description, as the server wrote it Read messages in a conversation. Requires the chat:read scope.
Annotations the server declares
- readOnlyHint: false
update_serviceEdit one of the human's service listings.No findings
Why it is in this group
- The name "update_service" says "update": a word for a change.
Description, as the server wrote it Edit one of the human's service listings. Requires the services:write scope.
Annotations the server declares
- readOnlyHint: false
Only reads 6Show 6 read-only tools
get_taskRead one task by id.1 finding
Why it is in this group
- The name "get_task" says "get": a word for reading.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "Read one task by id. Needs no credentials."
Description, as the server wrote it Read one task by id. Needs no credentials.
Annotations the server declares
- readOnlyHint: true
how_to_connectExplain how to connect an agent to a human on Day1Work: the device flow, the scopes, and what needs the human's approval.No findings
Why it is in this group
- The description's first verb is "explain": a word for reading.
Description, as the server wrote it Explain how to connect an agent to a human on Day1Work: the device flow, the scopes, and what needs the human's approval. Call this when you need to act for someone but have no token yet.
Annotations the server declares
- readOnlyHint: true
list_categoriesList the task categories on Day1Work, with icons.No findings
Why it is in this group
- The name "list_categories" says "list": a word for reading.
Description, as the server wrote it List the task categories on Day1Work, with icons.
Annotations the server declares
- readOnlyHint: true
list_servicesList services people offer (the work they sell) in a country.1 finding
Why it is in this group
- The name "list_services" says "list": a word for reading.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...work they sell) in a country. Needs no credentials."
Description, as the server wrote it List services people offer (the work they sell) in a country. Needs no credentials.
Annotations the server declares
- readOnlyHint: true
search_tasksSearch open tasks on Day1Work.1 finding
Why it is in this group
- The name "search_tasks" says "search": a word for reading.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...pen tasks on Day1Work. Reading needs no credentials. Country is a hard boundary: no listing..."
Description, as the server wrote it Search open tasks on Day1Work. Reading needs no credentials. Country is a hard boundary: no listing crosses a border. In-person tasks are returned only when you pass latitude and longitude, and only within that country's radius. Addresses are approximate and posters are not identified.
Annotations the server declares
- readOnlyHint: true
whoamiWho this agent is acting for, its scopes, its limits and what it has spent today.No findings
Why it is in this group
- The name "whoami" says "whoami": a word for reading.
Description, as the server wrote it Who this agent is acting for, its scopes, its limits and what it has spent today. Requires an agent token.
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.
8 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 outbound tools breaks every one.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__day1work__post_task",
"mcp__day1work__send_message"
]
}
}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, 18:37 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 9
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://api.day1work.com/.well-known/oauth-protected-resource
- Authorization servers
- https://api.day1work.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 9 tools that change things (2 irreversible, 7 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.day1work.com/mcp: tools/list returned 15 tools to an anonymous client, including send_message (irreversible), request_payment (irreversible), post_task (write), offer_service (write), update_service (write) and 4 more
Findings
Matches of fixed checks, with the text they matched.
The server marks "list_conversations" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false}; The name "list_conversations" says "list": a word for reading.
- Warnread_messages
The server marks "read_messages" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false}; The name "read_messages" says "read": a word for reading.
- Infosearch_tasks
The description mentions "credentials".
What this check looks forMatched text
description: "...pen tasks on Day1Work. Reading needs no credentials. Country is a hard boundary: no listing..."
- Infoget_task
The description mentions "credentials".
What this check looks forMatched text
description: "Read one task by id. Needs no credentials."
- Infolist_services
The description mentions "credentials".
What this check looks forMatched text
description: "...work they sell) in a country. Needs no credentials."
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http day1work https://api.day1work.com/mcpclaude mcp add --transport http day1work https://api.day1work.com/mcpRun 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__day1work__search_tasks",
"mcp__day1work__get_task",
"mcp__day1work__list_categories",
"mcp__day1work__list_services",
"mcp__day1work__how_to_connect",
"mcp__day1work__whoami"
],
"ask": [
"mcp__day1work__post_task",
"mcp__day1work__offer_service",
"mcp__day1work__update_service",
"mcp__day1work__bid_on_task",
"mcp__day1work__list_conversations",
"mcp__day1work__read_messages",
"mcp__day1work__send_message",
"mcp__day1work__request_payment",
"mcp__day1work__check_approvals"
],
"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 day1work. Review it before you use it.
Capability tags behind 4 rules
- mcp__day1work__post_task outbound
- mcp__day1work__list_conversations private-data, untrusted-input
- mcp__day1work__read_messages private-data, untrusted-input
- mcp__day1work__send_message outbound
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.day1work/day1work/verify?hash=f6f5e40dd94cf8abad08b51f48fcb01d71f10f5be5f854965fc6e16bdb3465a7" | jq -e '.changed == false'Pinned hash f6f5e40dd94c, from Nov 10, 2026, 14:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.day1work/day1work/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.day1work/day1work)Source: MCP Registry · repository. Synced Oct 21, 2026, 17:53 UTC.
day1work MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the day1work MCP server safe?
- No scan can promise that. What its definitions show: 15 tools, 9 of which can change, send or delete something, and 5 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the day1work MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the day1work MCP server do things that cannot be undone?
- Yes. 2 tools can send, pay, publish or merge: send_message and request_payment.
What tools does the day1work MCP server have?
- 15 tools: 2 irreversible, 7 write, 6 read. send_message, request_payment, post_task, offer_service, update_service, bid_on_task, list_conversations, read_messages and 7 more.
Does the day1work MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the day1work MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): post_task and send_message.
Has the day1work MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.