Tempo by Tempo

# Fix list: Tempo

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/tempo, the October 2026 research run, assessed 1 October 2026. Grade BB, 76.6 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on Tempo: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Reliability, 71 out of 100, up to 5.8 more on the total

Why it scored 71: Better Stack status page at status.tempo.xyz with seven components across mainnet, testnet and api.tempo.xyz (20). One incident in the last 90 days, the mainnet public RPC going down on 28 September 2026 and recovering by 09:19 UTC, with that component still at 99.996% for 30 days (20). Rate limits published, 100 requests a minute per key per scope and 20 a minute per IP for anonymous callers, read from `RateLimit-*` headers (15). 429s carry `Retry-After`, and the docs ask for exponential backoff with jitter; we found no idempotency guidance for the fee-payer relay (13 of 15). No SLA (0). Mainnet has run since 18 March 2026, but the API versioning page warns that "Endpoints are not yet stable and may change without notice" (3 of 10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 2. Security & auth, 70 out of 100, up to 5.3 more on the total

Why it scored 70: Project-scoped API keys with named scopes such as `data:read`, documented rotation and revocation, optional IP allowlists, environment prefixes (`tempo:sk:` and `tempo_sandbox:sk:`), and only a hash stored at rest. MPP payment credentials are kept separate from keys (30). Sandbox keys can't touch mainnet, most endpoints are read-only, and the console sets monthly spend and fee-sponsorship limits. Payments are signed by the agent's own wallet with no approval step on Tempo's side (16). Chain data such as token names and memos is attacker-controlled and we found no prompt-injection guidance (6). Console usage reports, `Payment-Receipt` headers and a public ledger (10). A SECURITY.md in the node repo, but the README says Tempo "is still undergoing audit and does not have an active bug bounty". No security.txt per the 30 September check. A security release (v1.13.1, 20 August 2026) was announced in the public changelog (8). Tempo doesn't hold user funds; wallets are self-custodied and stablecoins are issued by third parties.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 3. Agent ergonomics, 78 out of 100, up to 3.6 more on the total

Why it scored 78: The AI guide lists four documentation tools (`search`, `find_pages`, `read_page`, `code`), while the API reference describes data-domain tools plus docs search on the same host, so we can't size the tool list (15). Cursor pagination on every list endpoint, optional page pagination, and `limit` from 5 to 200 (18). Errors tell the agent to branch on `error.code` and point at the offending field, and the 402 for payment is protocol-native (18). Reads are safe to repeat, and the tempo CLI's `--dry-run` previews a payment's cost; we found no idempotency keys for writes (12). Public reads need no key and default to mainnet, with clients for TypeScript (viem/tempo, mppx), Python (pympp) and Rust (15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 4. Transparency & trust, 63 out of 100, up to 3.2 more on the total

Made of editorial 50, provenance 76.

Why it scored 63: The node is MIT or Apache-2.0, but the API, console, CLI and MCP server have no terms of service we could find (the 30 September check found none, and our fetch of tempo.xyz/terms was refused by our rate limit) (20). A privacy policy naming Tempo Labs Inc. exists per the 30 September check, which we couldn't reread, and the docs say API tokens are hashed at rest and redacted from logs (10). A written versioning and sunset policy, and every network upgrade in the changelog carries testnet and mainnet activation dates, though notice has been as short as three days (16). Stripe is named for console billing; no subprocessor list or data location found (4).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

Provenance checks not met in full (half of this category, computed from checked facts):

- Domain age: tempo.xyz, registered 2017-11-09 (8 years) (11 of 15)
- Terms of service: not found (0 of 10)
- security.txt: not found (0 of 10)

## 5. Payments & pricing, 80 out of 100, up to 2.5 more on the total

Why it scored 80: Payment platforms and wallets take the highest step that applies on the 40-point protocol line. 40 for x402, MPP or L402 on all their own endpoints, 30 on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, 0 for only a protocol of their own. api.tempo.xyz accepts MPP on every endpoint open to anonymous callers, either up front with `Authorization: Payment` or after a 402 challenge once over quota. The docs say most read endpoints are open, while key-only endpoints such as webhook management and the zone withdrawal reads don't take MPP, so the part-of-its-own-API step (30 of 40). Chain fees published, a base-fee cap of about $0.0006 and a floor of about $0.00003 for a 50,000-gas transfer, but API usage is billed through the console and we found no price for API calls or per MPP request (10). Public reads are free within quota and the Moderato testnet has a faucet, no card needed (20). An agent can read keyless and pay per request over MPP with no account (20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## 6. Schema & documentation, 88 out of 100, up to 2 more on the total

Why it scored 88: Public OpenAPI at api.tempo.xyz/openapi.json, which the docs build pulls for its API reference, plus OpenRPC for JSON-RPC (25). llms.txt with over 200 pages and Markdown pages (10). Per-domain API guides and a short tool table for the MCP server, but the AI guide and the API reference describe the MCP server's tools differently (14). Typed parameters such as `chainId` (mainnet, testnet or a number) and `limit` bounded to 5 to 200 (12). A single error envelope with stable `error.code`, field paths on validation errors and a request ID, plus a full code catalogue (14). `/v1` paths, a versioning policy with `Deprecation` and `Sunset` headers that applies once the API stabilises, and a dated node changelog (13).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## 7. Maintenance & community, 88 out of 100, up to 1.1 more on the total

Why it scored 88: Node v1.15.0 published on 24 September 2026, and tag v1.15.1 created on 1 October (30). v1.11.0, v1.12.0, v1.13.0 to v1.13.2, v1.14.0 and v1.15.0 since 22 July (20). 565 commits to the node repo since early July and a dated public changelog; we didn't read the issue queue (18 of 25). Current TypeScript, Python and Rust clients; we didn't check the MCP registry (10). CI runs tests, lint, semver checks, dependency scans and reproducible builds (10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- unchecked: terms of service and the current privacy policy; our fetches of tempo.xyz/terms and tempo.xyz/privacy-policy/ were refused by our own rate limit, so we rely on the 30 September check (privacy policy present, no terms found)
- unchecked: the OpenAPI document itself (api.tempo.xyz/openapi.json), refused by our rate limit; per-request MPP prices may be in it
- How many tools mcp.tempo.xyz exposes; the AI guide lists four documentation tools while the API reference describes data-domain tools on the same host
- Whether anonymous callers get 20 or 100 requests a minute; the rate-limits page says 20 per IP and the API MCP page says 100

## Weaknesses

- The API versioning page says endpoints are not yet stable and may change without notice
- No terms of service found for the API, console, CLI or MCP server
- No active bug bounty while audits continue
- Breaking network upgrades every two to four weeks, with mainnet activation as soon as three days after release
- No published price for API usage or per-request MPP payments

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Send `Authorization: Payment` up front to pay per request; a 402 after quota carries the challenge in `WWW-Authenticate`
- Read `RateLimit-Remaining` and `RateLimit-Reset` rather than hardcoding the 20 or 100 a minute defaults
- Pass `chainId=testnet` with a sandbox key; a sandbox key sent to mainnet is ignored and the call drops to the anonymous limit
- Use `tempo request --dry-run` before paying an MPP endpoint to see the cost
- Branch on `error.code`, never on `error.message`

## What the review panel asked for

- Price per paid request
- Terms of service
- a date for API stability
- a minimum notice before mainnet activation
- publish per-request MPP prices
- state one anonymous limit
- One table of MCP tools
- Reconcile the rate limit
- reconcile the rate-limit pages
- one MCP tool list
- Settle the anonymous limit
- Publish an SLA
- Publish per-request prices
- Reconcile the anonymous limit
- an active bug bounty
- published terms of service

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.