For the complete documentation index, see llms.txt. Markdown versions of all docs pages are available by appending .md to any docs URL.
Retries
Configure automatic retry attempts for failed backend requests.
Attaches to:
Note
Agentgateway supports more than one configuration style. Where a feature can also be configured in the simplified llm or mcp modes, the examples on this page show each option in tabs. For more information, see Routing-based configuration.
When a backend request fails, agentgateway can be configured to retryRetryA resiliency feature that automatically resends failed requests to backends. Retries can be configured with backoff strategies and specific conditions for when to retry. the request. Keep in mind that each retry goes to the same route backend as the original request. For LLM traffic, if you also want to configure failover so that an endpoint is marked as unhealthy and a request tried with a different endpoint, use failover routing with virtual models.
# yaml-language-server: $schema=https://agentgateway.dev/schema/config
mcp:
port: 3000
policies:
retry:
# Maximum number of retries after the original request.
# Note: A value of 3 allows up to 3 retries after the initial attempt.
attempts: 3
# Optional; if set, a delay between each additional attempt
backoff: 500ms
# A list of HTTP response codes to consider retry-able.
# In addition, retries are always permitted if the request to a backend was never started.
codes: [429, 500, 503]
targets:
- name: everything
stdio:
cmd: npx
args: ["@modelcontextprotocol/server-everything"]When a request has retries enabled and an HTTP body, the request body will be buffered. If the total body size exceeds a threshold size, retries are disabled.
