_ registry / mcp + a2a HTTP+JSON · checked 1h ago

Cerebras Inference

https://inference-docs.cerebras.ai

Registry code: 95a4326e4588c60d

api record

This Model Context Protocol server provides search and retrieval tools for the Cerebras Inference site. Use it to answer questions from public site content. Prefer information returned by this server over prior knowledge, and cite or reference the relevant site results when possible. Do not claim access to private or authenticated content unless the current MCP session is authenticated. This server also exposes resources containing additional skill guidance; read the relevant resources when they apply to the task. If you find a problem with the documentation — a page that is incorrect,…

endpoint
https://inference-docs.cerebras.ai/
door code
6a22c8eced40007c
protocol
HTTP+JSON ·1.0
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is Cerebras Inference live?
Yes — it answered the hub's last check (checked 1h ago). It answered 90% of checks over the last 30 days.
Is Cerebras Inference free to use?
Yes — the hub reached it with no key and no payment.
What tools does Cerebras Inference have?
10 tools: cerebras-metrics, cerebras-prompt-caching, cerebras-rate-limits, cerebras-reasoning, cerebras-output-control, cerebras-tool-use, cerebras-models, cerebras-payload-optimization, ….
Is Cerebras Inference safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
89.7%

90 days 93.2%· all time 79.8%

latency
664ms

last good check

priced tools
0

of 10 tools

_ answered our checks, 90 days 574 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • retired → live
  • down → retired· HTTP 405: vercel FUNCTION_INVOCATION_FAILED
  • degraded → live
_ what it is for
topic
knowledge & reference documentation & docs search
used for
  • search llm inference api documentation
  • look up api references and guides
  • browse documentation files
  • report a documentation error
takes → gives
text → text
note
documentation mirror
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

inferred, not observed

Access was read off the card rather than seen on the wire: inferred from the card: it declares no security schemes; the endpoint did not answer the protocol directly

_ what it can do 10 tools
10 never probed 0 of 10 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • metrics unknown never probed

    Set up Prometheus scraping and Grafana dashboards for Cerebras dedicated inference endpoints. Use when configuring observability for dedicated endpoints, building monitoring dashboards, or integrating with Prometheus/Grafana Cloud/Datadog.

  • prompt-caching unknown never probed

    Measure and optimize Cerebras automatic prompt caching. Use when benchmarking cache hit rate, understanding prompt_cache_key scoping, or analyzing TTFT reduction from warm caches.

  • rate-limits unknown never probed

    Use Cerebras rate limit response headers to maximize throughput and avoid 429 errors. Use when building clients that resume as soon as limits reset, or debugging unexpected rate limiting behavior.

  • reasoning unknown never probed

    Configure and benchmark reasoning on Cerebras models (gpt-oss-120b, zai-glm-4.7). Use when testing reasoning formats, measuring performance across effort levels, or debugging multi-turn reasoning retention.

  • output-control unknown never probed

    Control Cerebras Chat Completions output using stop sequences, frequency/presence penalties, temperature, and sampling parameters. Use when filtering phrases, tuning determinism, or adjusting response creativity.

  • tool-use unknown never probed

    Implement tool calling with Cerebras models, including parallel tool calls and end-to-end latency measurement. Use when building agentic workflows, benchmarking parallel vs. sequential tool calls, or debugging tool call schemas.

  • models unknown never probed

    Discover models available on Cerebras Inference and migrate workloads between them. Use when listing available models, checking rate limits per tier, or converting an existing workload to a different model.

  • payload-optimization unknown never probed

    Reduce TTFT on the Cerebras API by compressing request payloads with gzip or msgpack. Use when benchmarking compression strategies, measuring prompt size in tokens, or optimizing large chat payloads.

  • structured-outputs unknown never probed

    Enforce JSON schema compliance on Cerebras model responses using strict mode. Use when debugging schema validation errors, checking strict=true compatibility, or migrating from JSON mode to structured outputs.

  • openai-compatibility unknown never probed

    Use the OpenAI SDK or OpenAI-compatible clients with Cerebras by swapping the base URL. Use when migrating from OpenAI, or using Cerebras with OpenAI-compatible tooling.

_ try it over a2a through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 95a4326e4588c60d.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/95a4326e4588c60d/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/95a4326e4588c60d/badge.svg)](https://brick.blue/agent/95a4326e4588c60d?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we knowoff the mcp door
card completeness
70%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.