Make API + MCP by Make (Celonis)

# Fix list: Make API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/make, the October 2026 research run, assessed 1 October 2026. Grade C, 58.9 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 Make 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. Payments & pricing, 30 out of 100, up to 8.8 more on the total

Why it scored 30: No x402, MPP or L402 (0). Plan prices are public and priced in credits, one per module action, but we found no published per-credit price for extra bundles (10). Free plan of 1,000 credits a month with no card (20). A person signs up in the browser and creates a token per zone (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.

## 2. Reliability, 63 out of 100, up to 7.4 more on the total

Why it scored 63: Statuspage at status.make.com with incidents per zone (20). The history feed lists at least eight incidents between 2 and 31 July 2026, including about 200 EU1 scenarios auto-disabled on 22 July, about 250 scenarios failed on 31 July, login failures across zones on 17 July and failed connection authorisations on US2 on 20 July. The feed's newest item is from 31 July, so nothing was posted in August or September (10). API limits published per organisation, 60 calls a minute on Core, 120 on Pro, 240 on Teams and 1,000 on Enterprise (15). 429 documented with the advice to wait one minute, but no Retry-After header or backoff guidance, and no safe-retry advice for writes (8). No SLA on the pricing page (0). The API and the hosted MCP server aren't marked beta (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.

## 3. Agent ergonomics, 63 out of 100, up to 6 more on the total

Why it scored 63: Tools are one per on-demand scenario plus management tools on paid plans, and a token's access control limits which scenarios appear. We couldn't count the management tools (15). Documented pagination, sorting and filtering on list endpoints (20). Errors carry codes an agent can branch on, such as IM002 for insufficient rights and 429 for the rate limit (18). We found no tool annotations or idempotency keys (5). No official SDK, and the base URL changes per zone, six of them now (5).

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. Security & auth, 68 out of 100, up to 5.6 more on the total

Why it scored 68: Scoped API tokens with about 35 read and write scopes, OAuth 2.0 clients with refresh or PKCE on request, and OAuth for the MCP server (30). Less 10 because the MCP token can travel in the URL path (`/mcp/u/<token>`) as a documented option, per the 30 September check (20). Read scopes are separate from write scopes and each MCP token can be limited to chosen scenarios, with no confirmation step before a scenario runs (14). Scenario output often holds third-party text and we found no prompt-injection guidance (3). Audit logs kept 30 days, longer on Enterprise, plus run history through the API (13). SOC 2 Type II and SOC 3 audits, ISO 27001 for the enterprise platform, and a bug bounty page at make.com/en/bounty. No security.txt per the 30 September check (18).

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. Maintenance & community, 36 out of 100, up to 5.6 more on the total

Why it scored 36: The newest release-notes entry is white-label release 2026.05, which sets deadlines from 10 August 2026 onwards but carries no date of its own, and we found no dated change in the last 90 days (10). No dated entries found since July (0). Public release notes with dated deprecations and a community forum. We didn't test a support channel (8). Listed in the official MCP registry as `com.make/mcp-server` per the 30 September check (15). No official SDK, and the legacy npm MCP server has had no release since v0.5.0 (3).

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.

## 6. Schema & documentation, 66 out of 100, up to 5.5 more on the total

Why it scored 66: No OpenAPI file. MCP tools get typed inputs from each scenario's input definitions, so half credit (10). llms.txt with about 380 entries and a Markdown copy of every page (10). API reference pages state each endpoint's purpose. MCP tool descriptions come from whatever the scenario owner wrote (10). Typed, documented parameters on the API, and scenario inputs typed by their owner (10). A single error schema with `detail`, `message` and `code`, Make-specific codes (IM001 to IM102, SC403) and request examples (13). Versioned at /api/v2, with white-label release notes and dated deprecation notices (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. Transparency & trust, 75 out of 100, up to 2.2 more on the total

Made of editorial 59, provenance 90.

Why it scored 75: Closed service under published terms with Celonis, Inc. (15). Security page states AES-256 at rest, TLS 1.2 and 1.3 in transit, 30-day log retention and longer on Enterprise. We didn't find a subprocessor list or DPA on the pages we read (18). Dated deprecation notices for modules and models, for example Aircall modules stopping on 30 September 2026 and Amazon Seller Central orders modules retiring on 27 March 2027 (16). Zones disclosed (eu1, eu2, us1, us2, plus eu1 and us1 on make.celonis.com) and hosting on AWS, but no subprocessor list found (10).

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.

- unchecked: status.make.com/history and the front page, and the MCP server overview and rate-limiting pages, which our fetch proxy refused for its own rate limit
- Whether the API base for eu1 and us1 organisations has moved to make.celonis.com, or whether both hosts work
- How many management tools the MCP server lists on a paid plan, and whether they carry annotations
- The release date of white-label release 2026.05 and whether make.com cloud has a dated changelog elsewhere
- The price of extra credit bundles

## Weaknesses

- No published OpenAPI file and no official SDK
- Six zone hosts, including two on make.celonis.com, and calls to the wrong zone fail
- The MCP token can sit in the URL path, which leaks into logs
- Status feed shows at least eight incidents in July 2026, two of which failed or disabled about 200 to 250 scenarios
- No dated release-notes entry in the last 90 days

## 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.

- Find the organisation's zone first. It may be on make.com or make.celonis.com
- Set scenarios to on-demand scheduling so the MCP server lists them as tools
- Use the header form of the MCP token rather than the /mcp/u/<token> path form
- On a 429, wait a full minute. The limit resets per minute and no Retry-After is sent
- Check the `code` field on errors. IM002 means the token lacks rights, not that the resource is missing

## What the review panel asked for

- dated platform changelog
- retire the path token
- confirmation before runs

## 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.