Alpha Vantage

# Fix list: Alpha Vantage

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/alpha-vantage, the October 2026 research run, assessed 8 October 2026. Grade E, 41.3 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 Alpha Vantage: 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, 30 out of 100, up to 14 more on the total

Why it scored 30: Graded as a hosted service. No status page was found. The site links none and status.alphavantage.co has no valid certificate (0). With no page there is no incident history to read (5). Limits are published with numbers, 25 requests a day on a free key and 75 to 1,200 a minute on premium plans (15). No 429, Retry-After or backoff guidance was found, and in our test calls a missing key and an unknown function both returned HTTP 200 with a text field (0). No SLA was found, and the terms supply the service as is (0). The REST API is generally available (10). Total 30.

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, 32 out of 100, up to 11.9 more on the total

Why it scored 32: One key per account with no scopes, documented only as `apikey=` in the query string, and replaced by emailing support. The hosted MCP server adds OAuth 2 with PKCE, dynamic client registration and one read scope (20 less 10 for the query string, so 10). Every function is read-only (15 of 20). News, sentiment and earnings transcripts are third-party text, and no guidance on treating them as untrusted was found (5 of 15). No usage log or per-call record for the key holder was found (0 of 15). security.txt returns 404, and no disclosure policy, bug bounty or certification was found. A report of keys in plain-text logs, GitHub issue 13, was closed within three days in April 2026 (2 of 20). The server source still writes the key and tool arguments into its own analytics records. Total 32.

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. Schema & documentation, 46 out of 100, up to 8.8 more on the total

Why it scored 46: The surface graded is the REST API, with the official MCP server noted. No OpenAPI document was found for the API. The MCP server's tools carry typed inputs generated from Python signatures (10 of 25). `/llms.txt` returns 404, and the only Markdown is the MCP README (3 of 10). Each function has a purpose statement, a parameter list and a premium marker, with little on when not to use it (13 of 20). Required and optional parameters are marked and allowed values listed in prose, while MCP inputs such as `interval` are plain strings with no enums (8 of 15). Every function has demo URLs and code in four languages, but no error responses are documented (8 of 15). The API has no version and no changelog. The MCP repository's changelog stops at 0.3.2 on 27 February 2026 with later changes under Unreleased (4 of 15). Total 46.

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.

## 4. Payments & pricing, 30 out of 100, up to 8.8 more on the total

Why it scored 30: No x402, MPP or L402 (0). Five monthly plans are public with prices, sold by requests a minute and not by call (10). A free key gives 25 requests a day with no card (20). The key comes from a browser form that asks for a name and an email address, and no key API was found (0). Total 30.

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.

## 5. Agent ergonomics, 54 out of 100, up to 7.5 more on the total

Why it scored 54: `outputsize=compact` returns the latest 100 points, `datatype=csv` shortens long series, and the MCP server previews anything over 32,000 tokens with a link to the full data. No field selection (15 of 25). `limit` and time filters on news and a `month` parameter for intraday history, with no pagination elsewhere (10 of 20). Errors and limit notices arrive as HTTP 200 with free text under `Error Message` or `Information`, undocumented (5 of 20). Every call is a GET read, and all MCP tools carry readOnlyHint true and destructiveHint false (16 of 20). Few required parameters and sensible defaults. No official SDK, only a Python CLI and community libraries (8 of 15). Total 54.

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.

## 6. Transparency & trust, 48 out of 100, up to 4.6 more on the total

Made of editorial 36, provenance 59.

Why it scored 48: A closed service under short terms that are clear on scope, personal and non-commercial by default, with the MCP server under MIT (15 of 30). The privacy policy of 25 August 2025 describes the website, keeps personal data 'only for as long as is necessary' with no periods, and no DPA was found. It does not describe the request analytics visible in the MCP server source (8 of 30). No deprecation policy. The MCP README marks the key-in-URL connection deprecated with no date, and the changelog flags breaking changes (3 of 20). Google Analytics, Mixpanel, GitHub, GitLab, PayPal or Braintree and Stripe are named, and data is processed in the United States (10 of 20). Total 36.

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: alphavantage.co, no registry record we could read (0 of 15)
- Terms of service: published, but our reader couldn't read it (7 of 10)
- Privacy policy: published, but our reader couldn't read it (7 of 10)
- Status page: not found (0 of 10)
- security.txt: not found (0 of 10)

## 7. Maintenance & community, 63 out of 100, up to 3.2 more on the total

Why it scored 63: The MCP server repository, which a workflow deploys to the hosted server, had its last commit on 3 October 2026, and the site footer says it was updated in October 2026 (30). No tags, and the newest PyPI release is 17 March 2026, so there are no dated releases in the last 90 days, though the repository shows over 30 commits since 21 July (8 of 20). Pull requests 14 and 18 were merged within a day and issue 16 closed in a day, while issue 17, a reported startup crash, has been open since 4 September. Support is by email (10 of 25). The server sits in the official MCP registry under the vendor's GitHub namespace, with no official SDKs (12 of 15). The published package leaves its `mcp` dependency unpinned, and the workflows deploy and publish without a visible test run (3 of 10). Total 63.

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.

- Whether issue 13 was closed with a fix, since the current source still records the key in analytics events
- Whether `marketdata-mcp-server` 0.3.1 from PyPI crashes on startup as issue 17 reports. We did not run it
- Whether error and limit responses count against the daily quota
- The price and terms of commercial use
- unchecked: the domain registration date, because no RDAP service answered for alphavantage.co
- unchecked: the comments on GitHub issues 13 and 17, because the GitHub API rate limit was reached
- unchecked: the authenticated tool list of the hosted MCP server. The count of 132 is from the source

## Weaknesses

- The REST key is documented only as `apikey=` in the query string, with no scopes and no self-service rotation found
- Errors and limit notices return HTTP 200 with an `Error Message` or `Information` text field. No error reference, 429 or Retry-After guidance was found
- No status page, SLA, OpenAPI document, llms.txt, API version or API changelog was found
- The terms grant personal, non-commercial use only. Use on behalf of a company needs a written agreement
- PyPI still serves `marketdata-mcp-server` 0.3.1 from 16 March 2026, and an issue open since 4 September 2026 reports that it crashes on startup

## 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.

- Check every 200 response for `Error Message`, `Information` or `Note` keys before parsing data. The API does not signal failures or limits by status code
- Budget 25 requests a day on a free key. Real-time, 15-minute delayed and intraday US data, index data and several indicators need a premium plan
- Keep `outputsize=compact` unless full history is needed, and ask for `datatype=csv` on long series to cut tokens
- Use the hosted MCP server with OAuth at `https://mcp.alphavantage.co/mcp`. The `?apikey=` MCP URL is marked deprecated
- Confirm the owner's use is personal and non-commercial, or that a commercial agreement exists, before acting for a business

## 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.