Instacart Developer Platform API + MCP

# Fix list: Instacart Developer Platform API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/instacart, the October 2026 research run, assessed 14 October 2026. Grade D, 48.3 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 Instacart Developer Platform 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. Reliability, 22 out of 100, up to 15.6 more on the total

Why it scored 22: No status page was found. status.instacart.com did not answer (0 of 20), so there is no incident history (5 of 30). The docs say the API accepts a limited number of requests a second but give no figure (0 of 15). A 429 comes with advice to retry later and to contact Instacart if it repeats, with no Retry-After or backoff guidance, and the shopping list docs advise caching links instead of recreating them (7 of 15). No SLA (0 of 10). The API and MCP server are in production use with no beta label (10 of 10). Total 22.

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

Why it scored 20: No x402, MPP or L402 (0 of 40). No price is published, and no page says the API is free. The terms let Instacart add fees later (10 of 20). A development key is free and needs no card, but access starts with an application whose page could not be read (10 of 20). A person applies and a production key needs a demo review (0 of 20). Total 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.

## 3. Maintenance & community, 20 out of 100, up to 7 more on the total

Why it scored 20: The newest changelog entry is 18 June 2026, 118 days before this check (10 of 30). No entries in the last 90 days (0 of 20). A dated changelog, a developer support address and an Atlassian service desk (10 of 15). No Instacart server in the official MCP registry, which lists only a community server, and no official SDKs (0 of 15). No public package or repository to assess (0 of 10). Total 20.

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.

## 4. Security & auth, 61 out of 100, up to 6.8 more on the total

Why it scored 61: Revocable API keys with read-only, read-write and admin levels, separate development and production keys, and a documented rotation procedure (25 of 30). The tools only create pages. The person chooses the store and checks out on Instacart, so an agent cannot spend money (18 of 20). The API returns a link and retailer names, with no free text from third parties (10 of 15). The dashboard shows each key's creation, last use and usage statistics (8 of 15). docs.instacart.com has no security.txt, and the one on www.instacart.com could not be read because robots.txt disallows our crawler. No disclosure programme was confirmed (0 of 20). Total 61. The MCP server answered the MCP handshake and tools/list without a key. Tool calls were not tested.

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. Agent ergonomics, 71 out of 100, up to 4.7 more on the total

Why it scored 71: Two compact MCP tools (25 of 25). Responses are a single URL. The nearby retailers call filters by postal and country code, and line items take brand and health filters (15 of 20). Errors carry an internal code and a meta key that names the failing field (18 of 20). No idempotency keys and no readOnlyHint or destructiveHint annotations. Repeating a call creates another page, which costs nothing but a new link (5 of 20). Two required fields per tool. No official SDKs (8 of 15). Total 71.

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, 51 out of 100, up to 4.3 more on the total

Made of editorial 28, provenance 74.

Why it scored 51: Closed service with dated developer terms that are clear on restrictions and termination (15 of 30). The terms set security and privacy obligations for the developer and refer to a privacy addendum. The privacy policy itself is on www.instacart.com and was not read (8 of 30). The 18 March 2026 deprecation of quantity and unit was announced with a replacement but no removal date, and the terms allow changes without notice (5 of 20). No subprocessor list or data locations were found for the Developer Platform (0 of 20). Total 28.

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):

- 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: could not be fetched (0 of 10)

## 7. Schema & documentation, 80 out of 100, up to 3.3 more on the total

Why it scored 80: No public OpenAPI file was found for the Developer Platform API. Both MCP tools have typed JSON Schema inputs with required fields and additionalProperties false (20 of 25). llms.txt and a Markdown version of every page on docs.instacart.com (10 of 10). The REST reference explains each endpoint and its matching rules. The MCP descriptions are one line each and say nothing on when to use them (10 of 20). Required fields, minItems, enums for health filters and a 365-day cap on expires_in. MCP units are free text (11 of 15). Examples in curl, Java, Python and Go, and per-endpoint error tables with codes (14 of 15). Versioned paths (/idp/v1) and a dated changelog (15 of 15). Total 80.

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.

## 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.

- robots.txt on www.instacart.com disallows our crawler (User-Agent: * Disallow: /), so the privacy policy, consumer terms, the developer application page and any security.txt there were not read. The lander may hold this listing for that reason.
- unchecked: the privacy policy at https://www.instacart.com/company/privacy and the Instacart Privacy Addendum named in the developer terms.
- unchecked: whether tool calls on the MCP server reject a missing key. Only the handshake and tools/list were sent, without a key.
- unchecked: a vulnerability disclosure or bug bounty programme. The HackerOne page did not render for our reader.
- unchecked: the rate limit figure, which the docs do not publish.
- The API overview says to contact an Instacart representative for a key, while the key guide describes self-service creation in the dashboard after applying. The two pages disagree.

## Weaknesses

- No product search, price, order, order status or return endpoint. The person picks the store and checks out on Instacart
- Production keys need a screen-recorded demo and review, and Instacart puts access request to production at about 30 to 40 days
- No status page and no rate limit figure, only a 429 with advice to retry later
- The MCP tool schema still uses quantity and unit, which the REST API deprecated on 18 March 2026
- www.instacart.com disallows our crawler in robots.txt, so the privacy policy and application page were not read

## 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.

- Connect to https://mcp.instacart.com/mcp over Streamable HTTP with Authorization: Bearer and an Instacart Developer Platform key. Test against https://mcp.dev.instacart.tools/mcp with a development key
- Give the person the returned products_link_url to choose a store and check out. No call places or tracks an order
- Cache each generated link and create a new one only when the list changes, as the docs advise
- Send line_item_measurements rather than quantity and unit on the REST shopping list endpoint, since those fields are deprecated
- Do not show priced items from more than one retailer on one screen or move items between retailer baskets. The developer terms forbid both

## 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.