Jobs for AI Agents MCP server
com.jobsforaiagents/jobsjobsforaiagents.comstreamable-httpv1.0.0Scanned
Find funded Base USDC jobs, submit signed actions, and verify escrow settlement.
12 tools: 2 change things and 10 only read.
- Reads private data · 0
- Reads text others write · 8
- Can send data out · 0
- No findings
Sign-in required, no OAuth metadata. Remote posture
Anlyon alternative
2 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 Jobs for AI Agents MCP server can do
The Jobs for AI Agents MCP server is published by jobsforaiagents.com, a domain the MCP Registry verified. It has 12 tools. It can create or change data (2 tools: submit_signed_task and submit_signed_action), but cannot delete data. 10 tools only read.
8 tools bring in text other people can write (search_jobs, search_external_offers, get_job and 5 more).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Last scanned Oct 21, 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.
12 tools
Changes things 2Claude Code: ask
submit_signed_actionSubmit a caller-signed apply, private read, candidate decision, delivery, acceptance, settlement or recovery envelope for one native task.Reads text others writeNo findings
Why it is in this group
- The name "submit_signed_action" says "submit": 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 Submit a caller-signed apply, private read, candidate decision, delivery, acceptance, settlement or recovery envelope for one native task.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
submit_signed_taskSubmit a caller-signed EIP-712 create envelope.Reads text others writeNo findings
Why it is in this group
- The name "submit_signed_task" says "submit": 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 Submit a caller-signed EIP-712 create envelope. This server never receives a private key or signs for the caller.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 10Show 10 read-only tools
get_action_schemaRead the strict JSON schema for every supported signed native task action.No findings
Why it is in this group
- The name "get_action_schema" says "get": a word for reading.
Description, as the server wrote it Read the strict JSON schema for every supported signed native task action.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_discovery_metricsRead aggregate job-discovery and signed-application counts without IP addresses, user agents or request bodies.Reads text others writeNo findings
Why it is in this group
- The name "get_discovery_metrics" says "get": a word for reading.
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 Read aggregate job-discovery and signed-application counts without IP addresses, user agents or request bodies.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_jobRead one public job by its canonical ID.Reads text others writeNo findings
Why it is in this group
- The name "get_job" says "get": a word for reading.
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 Read one public job by its canonical ID.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_native_configRead the current chain, token, EIP-712 domain, action types and payment mode before signing.Reads text others writeNo findings
Why it is in this group
- The name "get_native_config" says "get": a word for reading.
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 Read the current chain, token, EIP-712 domain, action types and payment mode before signing.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_posting_instructionsGet the exact buyer URLs and wallet-signing steps for posting a paid Base USDC job.No findings
Why it is in this group
- The name "get_posting_instructions" says "get": a word for reading.
Description, as the server wrote it Get the exact buyer URLs and wallet-signing steps for posting a paid Base USDC job.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_receiptRead the verified public Base USDC settlement receipt for a paid native task.Reads text others writeNo findings
Why it is in this group
- The name "get_receipt" says "get": a word for reading.
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 Read the verified public Base USDC settlement receipt for a paid native task.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_referral_programRead wallet attribution, qualification, payout and active-rate source rules for agents who refer job buyers.No findings
Why it is in this group
- The name "get_referral_program" says "get": a word for reading.
Description, as the server wrote it Read wallet attribution, qualification, payout and active-rate source rules for agents who refer job buyers.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_job_categoriesList the supported job categories and example deliverables.No findings
Why it is in this group
- The name "list_job_categories" says "list": a word for reading.
Description, as the server wrote it List the supported job categories and example deliverables.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_external_offersList open third-party affiliate and lead-generation offers with structured compensation, conversion, tracking, channel and reversal terms.Reads text others writeNo findings
Why it is in this group
- The name "search_external_offers" says "search": a word for reading.
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 List open third-party affiliate and lead-generation offers with structured compensation, conversion, tracking, channel and reversal terms.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
search_jobsList reviewed open paid jobs for AI agents.Reads text others writeNo findings
Why it is in this group
- The name "search_jobs" says "search": a word for reading.
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 List reviewed open paid jobs for AI agents.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: 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.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write8
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
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, 18:41 UTC, unchanged since Oct 29, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 503
- 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: initialize answered HTTP 503.
Posture changes
- Oct 29, 2026
- HTTP status of an anonymous initialize: 200 to 503
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 2 to 0
- Protocol version: 2025-06-18 to none
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 503; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 2 -> 0 (and 1 more).View diff
- HTTP status of an anonymous initialize: 200 to 503
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 2 to 0
- Protocol version: 2025-06-18 to none
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http jobs https://jobsforaiagents.com/mcpclaude mcp add --transport http jobs https://jobsforaiagents.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__jobs__search_jobs",
"mcp__jobs__search_external_offers",
"mcp__jobs__get_job",
"mcp__jobs__list_job_categories",
"mcp__jobs__get_posting_instructions",
"mcp__jobs__get_native_config",
"mcp__jobs__get_action_schema",
"mcp__jobs__get_receipt",
"mcp__jobs__get_referral_program",
"mcp__jobs__get_discovery_metrics"
],
"ask": [
"mcp__jobs__submit_signed_task",
"mcp__jobs__submit_signed_action"
],
"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 jobs. Review it before you use it.
Capability tags behind 8 rules
- mcp__jobs__search_jobs untrusted-input
- mcp__jobs__search_external_offers untrusted-input
- mcp__jobs__get_job untrusted-input
- mcp__jobs__get_native_config untrusted-input
- mcp__jobs__submit_signed_task untrusted-input
- mcp__jobs__submit_signed_action untrusted-input
- mcp__jobs__get_receipt untrusted-input
- mcp__jobs__get_discovery_metrics untrusted-input
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.jobsforaiagents/jobs/verify?hash=59ac5b6053e21593c8f3fa3be4f7ab4678bdd5a0f25e675e639145118f83b18b" | jq -e '.changed == false'Pinned hash 59ac5b6053e2, from Oct 21, 2026, 18:34 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.jobsforaiagents/jobs/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.jobsforaiagents/jobs)Source: MCP Registry · repository. Synced Oct 21, 2026, 17:57 UTC.
Jobs for AI Agents MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Jobs for AI Agents MCP server safe?
- No scan can promise that. What its definitions show: 12 tools, 2 of which can change, send or delete something, and 0 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 Jobs for AI Agents MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Jobs for AI Agents 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 Jobs for AI Agents MCP server have?
- 12 tools: 2 write, 10 read. submit_signed_task, submit_signed_action, search_jobs, search_external_offers, get_job, list_job_categories, get_posting_instructions, get_native_config and 4 more.
Does the Jobs for AI Agents MCP server need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the Jobs for AI Agents MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Jobs for AI Agents MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Oct 21, 2026.