AI & frontier-lab job market: search roles, browse labs, track new postings since last check.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Roles added or changed since an ISO timestamp — poll this on a schedule (heartbeat) instead of re-fetching the whole feed.
ISO 8601 timestamp, e.g. 2026-10-29T00:00:00Z
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http frontier-ai https://superintelligence.jobs/mcp
Roles added or changed since an ISO timestamp — poll this on a schedule (heartbeat) instead of re-fetching the whole feed.
| Argument | Type | Description |
|---|---|---|
| since* | string | ISO 8601 timestamp, e.g. 2026-10-29T00:00:00Z |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"since"
],
"properties": {
"since": {
"type": "string",
"description": "ISO 8601 timestamp, e.g. 2026-10-29T00:00:00Z"
}
}
}Full detail for one role by id (from search_jobs), including applyUrl, compensation, skills, geography and freshness timestamps.
| Argument | Type | Description |
|---|---|---|
| id* | string | Role id, e.g. "anthropic-abc123" |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"description": "Role id, e.g. \"anthropic-abc123\""
}
}
}All tracked organizations with type, mission and current open-role counts.
No arguments.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}Dated aggregate numbers: open roles, organizations, distribution by category/mode/level. Stable facts for citation.
No arguments.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}Search open frontier-AI roles. Filters combine (AND). Returns compact records; use get_job for full detail.
| Argument | Type | Description |
|---|---|---|
| mode | string | Remote, Hybrid or On-site |
| level | string | e.g. Senior, Staff, Entry |
| limit | integer | Results per page (default 25) |
| query | string | Keyword across title, summary, category, skills |
| offset | integer | Pagination offset |
| company | string | Organization name or id, e.g. "Anthropic" |
| country | string | Country name, e.g. "United States" |
| category | string | e.g. Engineering, Research, Policy |
| remoteOnly | boolean | Remote roles only |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"mode": {
"type": "string",
"description": "Remote, Hybrid or On-site"
},
"level": {
"type": "string",
"description": "e.g. Senior, Staff, Entry"
},
"limit": {
"type": "integer",
"maximum": 100,
"minimum": 1,
"description": "Results per page (default 25)"
},
"query": {
"type": "string",
"description": "Keyword across title, summary, category, skills"
},
"offset": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": 0,
"description": "Pagination offset"
},
"company": {
"type": "string",
"description": "Organization name or id, e.g. \"Anthropic\""
},
"country": {
"type": "string",
"description": "Country name, e.g. \"United States\""
},
"category": {
"type": "string",
"description": "e.g. Engineering, Research, Policy"
},
"remoteOnly": {
"type": "boolean",
"description": "Remote roles only"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Oct 30, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.