Streak API + MCP by Streak

# Fix list: Streak API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/streak, the October 2026 research run, assessed 1 October 2026. Grade D, 46.5 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 Streak API + MCP: 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. Agent ergonomics, 28 out of 100, up to 11.7 more on the total

Why it scored 28: MCP tool list and count not published, so context cost can't be judged, and we found no response-size controls in the API docs we read (8 of 25). Pagination isn't covered in the docs we read (8 of 20). Errors are status codes with an unspecified JSON body (5 of 20). No idempotency keys or tool annotations found. Claude's connector settings let a user allow, block or approve each action, which is the client's control, not Streak's (4 of 20). No official SDK (3 of 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.

## 2. Schema & documentation, 35 out of 100, up to 10.6 more on the total

Why it scored 35: No OpenAPI or other machine-readable spec found (0). llms.txt on streak.readme.io per the 30 September check (10). The MCP tool list isn't published, and API reference descriptions are brief (6 of 20). Typed parameters in the readme.io reference (8 of 15). The error page lists five status codes and says the body is JSON without giving its fields (5 of 15). v1 and v2 paths and a product updates page, but no API changelog (6 of 15).

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.

## 3. Payments & pricing, 20 out of 100, up to 10 more on the total

Why it scored 20: No x402, MPP or L402 (0). Plan prices public, Pro $49 or $59, Pro+ $69 or $89, Enterprise $129 or $159 a user a month, nothing per call (10). The free plan has no CRM pipelines, so no useful API or MCP access, and the pricing page doesn't say whether the 14-day Pro+ trial needs a card (10 of 20). A person signs up through Gmail (0).

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.

## 4. Security & auth, 52 out of 100, up to 8.4 more on the total

Why it scored 52: REST takes an API key over HTTP Basic with all of the user's privileges. Keys can be deleted and recreated. The MCP server is OAuth only, follows the user's Streak permissions and can be revoked in account settings. No OAuth for REST apps found (22 of 30). No scopes or read-only mode on either route (6 of 20). The MCP server doesn't expose email content, which removes the largest source of outside text, but comments and box fields can still carry it, and we found no injection guidance (8 of 15). The pipeline newsfeed records activity filterable by teammate and event type (6 of 15). HackerOne bug bounty, a yearly Google OAuth review, hosting on Google Cloud in the US. No SOC 2 named, and no security.txt per the 30 September check (10 of 20).

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.

## 5. Reliability, 68 out of 100, up to 6.4 more on the total

Why it scored 68: Status page at status.streak.com with an RSS history (20). No incidents since 3 July 2026. The feed's only entry is a 9.5-hour delay in automatic email filtering on 1 June 2026, so the history is short (30). No hard rate limit. Streak asks to be told before you pass 10 requests a second and notes Google's 20-a-second project limit (8 of 15). No 429 behaviour, Retry-After or retry guidance documented (0). No SLA found (0). The MCP server carries no beta label (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.

## 6. Maintenance & community, 60 out of 100, up to 3.5 more on the total

Why it scored 60: Product update on 16 September 2026, with MCP changes on 1 June and 4 August (Claude connector) (30). Seven dated updates since 3 July 2026 (20). Public updates page and support. We didn't test support (10 of 15). Not in the official MCP registry and no official SDK (0). No packages to judge (0).

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.

## 7. Transparency & trust, 66 out of 100, up to 3 more on the total

Made of editorial 41, provenance 90.

Why it scored 66: Closed service with terms naming Rewardly, Inc. d/b/a Streak (15). Privacy policy last updated 27 September 2024, before the MCP server and AI tools shipped. It has no retention periods or subprocessor list, but does commit to Google's Limited Use rules and not training models on Workspace data. The security page says email content isn't stored (14 of 30). The API returns 410 for unsupported versions, but we found no deprecation policy or dated notices (4 of 20). Hosting on Google Cloud in the US is stated, with no subprocessor list (8 of 20).

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):

- security.txt: not found (0 of 10)

## 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.

- The MCP server's tool list, count and annotations, none published
- Whether the 14-day Pro+ trial needs a card
- Whether the API enforces any limit in practice, since the docs say there's no hard limit

## Weaknesses

- MCP tool list and count not published
- No OpenAPI, no documented 429 behaviour and no retry guidance
- REST keys carry the user's full privileges with no scopes
- Privacy policy last updated 27 September 2024, with no retention periods or subprocessor list
- API needs Pro ($49 a user a month yearly) and webhooks need Pro+

## 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.

- Keep under 10 requests a second, or tell Streak first, since there's no published hard limit
- Expect no email bodies through MCP and fetch thread context through Gmail instead
- Send the API key as the Basic auth username with an empty password
- Check the plan before relying on webhooks, which start at Pro+
- Handle a 410 as an API version that's no longer supported

## What the review panel asked for

- publish the MCP tool list
- document error fields
- published MCP tool list
- read-only scopes

## 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.