Salesforce API + MCP by Salesforce

# Fix list: Salesforce API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/salesforce, the October 2026 research run, assessed 1 October 2026. Grade C, 60.7 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 Salesforce 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). Per-user edition prices are public per the 30 September check (Pro Suite $100 plus $25 for API, Core $195), but hosted MCP use may bill against Flex Credits at a rate we didn't find. The pricing page returned 403 today (10). Developer Edition orgs are free and include hosted MCP for testing, per the 30 September check (20). A person signs up and an admin configures the app (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, 58 out of 100, up to 8.4 more on the total

Why it scored 58: Public status site with an incidents API at api.status.salesforce.com (20). The first page of incidents since 3 July 2026 lists 16, three marked major, including a core service disruption across more than 160 instances from 29 to 31 August and a core degradation across more than 200 instances for 17 hours on 3 September. None is labelled as the REST API or hosted MCP (5). Daily API allocations published by edition and licence (100,000 plus 1,000 per Salesforce licence on Enterprise, 15,000 on Developer Edition) and 25 concurrent long-running requests in production (15). Limit breaches return `REQUEST_LIMIT_EXCEEDED` and responses carry `Sforce-Limit-Info`. No Retry-After or idempotency keys found (8 of 15). No SLA found (0). Hosted MCP servers are GA (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. Maintenance & community, 18 out of 100, up to 7.2 more on the total

Why it scored 18: No hosted MCP changelog yet ('Changelog coming soon'). The GA came in April 2026 per the listing, between 90 and 180 days before the run (10). No dated hosted MCP changes found in the last 90 days (0). Platform release notes and the Trailblazer community, but nothing MCP-specific to follow (8 of 15). Not in the official MCP registry, which lists only third-party Salesforce servers, and no official general-purpose REST 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.

## 4. Security & auth, 72 out of 100, up to 4.9 more on the total

Why it scored 72: Per-user OAuth 2.0 with PKCE through an External Client App, with only `mcp_api` and `refresh_token` scopes, every call inside the user's field-level security and sharing rules, and no API-key path (30). Servers are off by default and enabled one at a time. Reads, Mutations and Deletes give least privilege, and delete tools ask for confirmation (20). Record text written by outsiders reaches the model, and the hosted MCP docs give no injection guidance (4 of 15). The platform has setup audit trails and event monitoring, but the MCP docs don't mention logging of MCP calls (8 of 15). The compliance portal links a responsible disclosure page, and the DX MCP repository points reports to sfdc.co/SubmitVuln. The compliance portal renders client-side, so certifications are unchecked. No security.txt (404) (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. Schema & documentation, 76 out of 100, up to 3.9 more on the total

Why it scored 76: The hosted MCP reference documents each tool's parameters. We didn't read the live tools/list, and the listing has no OpenAPI for REST (20 of 25). llms.txt on developer.salesforce.com per the 30 September check (10). Tool descriptions are written for models. `getObjectSchema` returns schema `optimized for LLM consumption`, SOQL must carry WHERE and LIMIT, and deletes ask the user first (17 of 20). The main read path is a free-form SOQL string (9 of 15). Examples in the reference. We didn't find an error reference for the MCP servers (10 of 15). REST is versioned (v66.0) with platform release notes, but the hosted MCP docs say 'Changelog coming soon' (10 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.

## 6. Agent ergonomics, 76 out of 100, up to 3.9 more on the total

Why it scored 76: SObject All has 11 tools (15). SObject Reads, Mutations and Deletes split the same tools by risk, so an operator can load only what's needed (10 more, 25). SOQL takes LIMIT, `find` caps at 2,000 records, and `getObjectSchema` has index and detail modes (20). We didn't check the error format (12 of 20). Delete tools ask for confirmation, the servers are split by risk, and deleted records sit in a 15-day recycle bin. No annotations or idempotency keys documented (12 of 20). An admin has to create an External Client App and switch on each server. No official general-purpose REST SDK found (7 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.

## 7. Transparency & trust, 74 out of 100, up to 2.3 more on the total

Made of editorial 57, provenance 90.

Why it scored 74: Closed service with terms naming Salesforce, Inc. (15). Privacy statement updated 19 May 2026, with Binding Corporate Rules, the Data Privacy Framework and SCCs. Retention reads 'consistent with the original purpose', and there's no statement on training AI with customer data (20 of 30). The beta-to-GA page documents what changed (new URL, servers off by default, narrower scopes, beta tokens invalid), but no hosted MCP deprecation policy (10 of 20). Subprocessors and infrastructure are covered in linked trust and compliance documents we didn't read (12 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.

- unchecked: current Sales Cloud prices and API add-on, the pricing page returned 403. Relying on the 30 September check
- unchecked: Salesforce certifications, because the compliance portal renders client-side
- unchecked: whether the incidents API returned every incident since 3 July or only a first page
- The Flex Credit rate for hosted MCP calls
- Whether hosted MCP tools set readOnlyHint or destructiveHint

## Weaknesses

- No hosted MCP changelog yet
- API access needs the $25 add-on on Pro Suite or a Core seat at $195, and Free and Starter suites have none
- MCP usage may bill against Flex Credits at a rate we couldn't find
- Multi-day core service incidents across more than 160 instances in late August 2026
- No security.txt, and the main read tool takes free-form SOQL

## 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.

- Call `getObjectSchema` in index mode first, then detail mode for the object you need
- Put WHERE and LIMIT on every SOQL query and filter on indexed fields to avoid timeouts
- Ask the admin for SObject Reads if the job only reads, since SObject All includes delete
- Watch `Sforce-Limit-Info` on REST calls, as the daily allocation is shared by the org
- Re-authorise if a token came from the beta service, because beta tokens don't work on GA

## What the review panel asked for

- publish an MCP error reference
- publish a changelog
- MCP call audit logs
- injection guidance

## 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.