Slack MCP Server (official) by Slack (Salesforce)

# Fix list: Slack MCP Server (official)

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/slack-mcp, the October 2026 research run, assessed 1 October 2026. Grade C, 59.8 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 Slack MCP Server (official): 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, 20 out of 100, up to 10 more on the total

Why it scored 20: No x402, MPP or L402 (0). No separate MCP charge, and Slack's plan prices are public (10). Slack has a Free plan without a card, but we didn't confirm MCP access on it (10). A person registers or installs a Slack app and signs in through OAuth (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. Agent ergonomics, 51 out of 100, up to 8 more on the total

Why it scored 51: 23 tools with no toolsets, read-only subset or dynamic loading (15). Search filters by date, user and content, list_user_channels paginates, and read_channel takes oldest and latest (16). No documented error responses (4). No idempotency keys, and we couldn't check readOnlyHint or destructiveHint. Private search asks the user for consent first (6). One URL, but each operator needs a registered Slack app unless the client ships Slack's own client ID, and Slack maintains SDKs in JavaScript, Python and Java (10).

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.

## 3. Schema & documentation, 57 out of 100, up to 7 more on the total

Why it scored 57: Tools carry JSON Schema by protocol, but Slack doesn't publish the schemas, only a list of 23 tools with the scope each needs (15). No llms.txt per the 26 September check, though Slack's plugin reads the docs as Markdown (3). The official skills say when to pick each tool, for example slack_search_public needs no user consent and slack_search_public_and_private does (14). Input types not visible, the skills mention oldest and latest timestamps on slack_read_channel (7). Usage examples in the skills, no documented MCP error responses (8). MCP changes are logged in the platform changelog (17 February, 13 May and 31 July 2026) with no version on the tool surface (10).

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

Why it scored 68: Slack's own status page at slack-status.com with a history API and an Apps/Integrations/APIs component, but no MCP component (15). Four minor incidents and no outages in the last 90 days (reminders 23 July, workflows 24 July, email receipt 27 July, free-plan message failures 1 October 2026), none naming MCP (20). Every tool sits on a published Web API tier, Tier 2 at 20+ a minute, Tier 3 at 50+ and Tier 4 at 100+, with search and send on special limits (15). The MCP page gives no 429 or Retry-After guidance and we didn't check the Web API rate-limit page in this run (5). The SLA dated 11 July 2024 promises commercially reasonable efforts with no percentage or credits (3). GA since 17 February 2026 (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.

## 5. Security & auth, 79 out of 100, up to 3.7 more on the total

Why it scored 79: OAuth with user tokens only, a confidential client, per-tool scopes and RFC 8414 metadata. No secrets in URLs (30). Scopes can be limited to read tools, workspace admins approve every MCP client through app approval, and searching private channels and DMs requires user consent, but there's no read-only endpoint (16). Tools return messages and files anyone in the workspace can write, and the docs only say to use judgement (3). MCP calls get their own audit-log entries tied to a fixed app ID, and IP allowlists apply (13). security.txt valid per the 26 September check, SOC 2 Type II, ISO 27001 and ISO 42001 and FedRAMP Moderate on the compliance page, which doesn't mention a bug bounty (17).

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.

## 6. Maintenance & community, 58 out of 100, up to 3.7 more on the total

Why it scored 58: Last dated MCP entry in Slack's changelog on 31 July 2026, the MCP and skills plugin, 62 days before the run date (20). The official plugin that wires up the server shipped 1.2.0 on 30 July, 1.3.0 on 24 August and 1.4.0 on 24 September 2026 (20). Closed service with a public changelog and support, and we didn't read the plugin repository's issues (10). Not in the official MCP registry under a Slack namespace (0). The plugin repository runs CI and dependency updates (8).

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, 83 out of 100, up to 1.5 more on the total

Made of editorial 66, provenance 100.

Why it scored 83: Closed service under Slack's terms, with the plugin under MIT (15). Privacy policy, DPA and subprocessor pages exist, but we found no MCP-specific statement on what partners may keep from search results and didn't read the DPA in this run (18). Deprecations carry dates, such as assistant_view retiring in February 2027 announced on 20 August 2026 (15). A subprocessor page naming identity, location and role, and a data-residency article (18).

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.

## 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 the MCP server is available on Slack's Free plan.
- Whether tools set readOnlyHint and destructiveHint, and what errors they return when a scope or tier limit is hit.
- unchecked: Slack's Web API rate-limit page for Retry-After behaviour, and its DPA.
- Whether Slack runs a public bug bounty today, which the compliance page doesn't mention.

## Weaknesses

- Unlisted apps are barred, so other clients need a Marketplace or internal app
- No read-only endpoint, toolsets or Dynamic Client Registration
- Tool schemas and error responses aren't published
- Not listed in the official MCP registry
- The SLA promises commercially reasonable efforts with no uptime figure

## 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.

- Use `slack_search_public` unless the task needs private channels, the private variant asks the user for consent
- Read the latest messages with `slack_read_channel`, search lags by a few seconds
- Keep emoji, user and channel searches under 20 calls a minute, they sit on Tier 2
- Outside Claude Code and Cursor, register a Marketplace or internal Slack app first, there's no anonymous path

## What the review panel asked for

- Publish input schemas
- Document error responses
- read-only endpoint
- published tool annotations

## 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.