Real-time API status & breaking-change oracle for AI agents
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Optional AgentPulse API key as a Bearer token. Public status tools work without it; identified tools (get_my_impact, report_outage_signal) and higher quota require it. Get a free key via POST /v1/agents/register.
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.
Preflight dependency health check for AI coding & devops agents. Evaluates if third-party APIs or cloud providers are experiencing outages, rate-limit spikes, or silent failures before wasting tokens retrying failing calls.
List of service slugs to check (e.g. ["stripe", "openai", "supabase", "resend", "aws", "github"])
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.
Run in a terminal
claude mcp add --transport http agentpulse https://agentpulse-43di.onrender.com/mcp
Headers
Authorization (optional, not in the config above): Optional AgentPulse API key as a Bearer token. Public status tools work without it; identified tools (get_my_impact, report_outage_signal) and higher quota require it. Get a free key via POST /v1/agents/register.Preflight dependency health check for AI coding & devops agents. Evaluates if third-party APIs or cloud providers are experiencing outages, rate-limit spikes, or silent failures before wasting tokens retrying failing calls.
| Argument | Type | Description |
|---|---|---|
| dependencies* | array | List of service slugs to check (e.g. ["stripe", "openai", "supabase", "resend", "aws", "github"]) |
{
"type": "object",
"required": [
"dependencies"
],
"properties": {
"dependencies": {
"type": "array",
"items": {
"type": "string"
},
"description": "List of service slugs to check (e.g. [\"stripe\", \"openai\", \"supabase\", \"resend\", \"aws\", \"github\"])"
}
}
}Returns "affected code" verdicts for the calling agent's stored dependency manifest (set via PUT /v1/agents/me/dependencies): for each dependency, whether an active incident or a breaking change detected in the last 90 days affects it, with matching incident/change ids and a one-line reason. Identity comes from the Authorization: Bearer <api_key> header (same as REST); an api_key argument is accepted as a fallback.
| Argument | Type | Description |
|---|---|---|
| api_key | string | Optional AgentPulse API key (agp_live_...). Only needed when the Authorization header is not sent. |
{
"type": "object",
"required": [],
"properties": {
"api_key": {
"type": "string",
"description": "Optional AgentPulse API key (agp_live_...). Only needed when the Authorization header is not sent."
}
}
}Retrieve real-time health, active incidents, affected scope, and prescriptive agent_hint for a single cloud provider or API in < 150 tokens.
| Argument | Type | Description |
|---|---|---|
| service* | string | Service slug (e.g. "stripe", "openai", "anthropic", "github", "aws") |
{
"type": "object",
"required": [
"service"
],
"properties": {
"service": {
"type": "string",
"description": "Service slug (e.g. \"stripe\", \"openai\", \"anthropic\", \"github\", \"aws\")"
}
}
}Query recent API deprecations, schema diffs, and breaking changes for a cloud service or package before invoking SDKs.
| Argument | Type | Description |
|---|---|---|
| since | string | Optional ISO 8601 timestamp checkpoint (e.g. "2026-01-01T00:00:00Z") |
| service* | string | Service slug (e.g. "openai", "stripe", "supabase", "aws") |
{
"type": "object",
"required": [
"service"
],
"properties": {
"since": {
"type": "string",
"description": "Optional ISO 8601 timestamp checkpoint (e.g. \"2026-01-01T00:00:00Z\")"
},
"service": {
"type": "string",
"description": "Service slug (e.g. \"openai\", \"stripe\", \"supabase\", \"aws\")"
}
}
}Submit an observed 5xx error spike, timeout, or rate-limit anomaly to crowdsource early outage detection across the agent ecosystem. Requires the calling agent's API key (Authorization: Bearer header or api_key argument) — anonymous signals are rejected.
| Argument | Type | Description |
|---|---|---|
| service* | string | Service slug where failure was observed |
| endpoint* | string | Affected HTTP endpoint or method (e.g. POST /v1/chat/completions) |
| error_code* | integer | HTTP status code observed (e.g. 500, 502, 503, 504, 429) |
| error_type | string | Optional error description or category |
{
"type": "object",
"required": [
"service",
"endpoint",
"error_code"
],
"properties": {
"service": {
"type": "string",
"description": "Service slug where failure was observed"
},
"endpoint": {
"type": "string",
"description": "Affected HTTP endpoint or method (e.g. POST /v1/chat/completions)"
},
"error_code": {
"type": "integer",
"description": "HTTP status code observed (e.g. 500, 502, 503, 504, 429)"
},
"error_type": {
"type": "string",
"description": "Optional error description or category"
}
}
}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 Nov 22, 2026.
Takes a password, API key or token as an argument, so the secret passes through the model's context and chat logs.
Fix: Read credentials from the server's own configuration (environment, OAuth) instead of a tool argument.
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.