Galileo API + MCP by Galileo (now Splunk Agent Observability, Cisco)

# Fix list: Galileo API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/galileo, the October 2026 research run, assessed 1 October 2026. Grade D, 48 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 Galileo 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, 18 out of 100, up to 16.4 more on the total

Why it scored 18: No status page found. status.galileo.ai doesn't resolve and neither the homepage, the docs nor the Splunk docs link one (0). With no history to read, 5. No rate limits published for Galileo's own API. The pricing page lists custom rate limits on Enterprise only (0). The error catalogue marks each error retriable or not and the Python SDK raises a named `RateLimitError` on 429, but the 429 entries cover AI-provider limits, the OpenAPI spec declares no 429 and we found no `Retry-After` guidance (5). No SLA on any plan (0). The REST API is GA. The MCP server is labelled under construction until it reaches general availability (8).

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, 33 out of 100, up to 11.7 more on the total

Why it scored 33: API key in a header (`Splunk-AO-API-Key` in the current spec, `Galileo-API-Key` in older docs), a JWT from `/login/api_key` that expires after 24 hours, or HTTP Basic with a username and password, which the docs list as an option. We found no key scopes, expiry or rotation docs (18). Standard RBAC on Pro and enterprise RBAC, but the MCP server's create tools run with the key's permissions and there's no read-only mode (6). Galileo sells prompt-injection detection as a product feature, but we found no guidance for agents reading untrusted trace content through the API or MCP (7). No audit log found (0). No security.txt, no trust page (trust.galileo.ai doesn't resolve, galileo.ai/security is a 404), no SECURITY.md in either SDK repository and no SOC 2, ISO or HIPAA claim on the homepage, pricing page or privacy policy (2).

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

Why it scored 20: No x402 or other machine payment (0). Plan prices are public, Pro at $100 a month billed yearly for 50,000 traces, but overage only "scales based on number of traces" (10). The Free plan exists with 5,000 traces a month. The pricing page doesn't say whether a card is needed, so half (10). A person signs up in a browser at app.galileo.ai/sign-up (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.

## 4. Agent ergonomics, 73 out of 100, up to 4.4 more on the total

Why it scored 73: The MCP server has 8 tools, compact, but only `Get Signals` reads production data. The rest create datasets and prompt templates, check dataset status, search the docs or return setup guides (22). `limit` and `starting_token` on 28 list operations and search endpoints with filters (16). The error catalogue gives an agent a code, a fix and whether to retry (16). No idempotency keys or safe-retry guidance found, and no tool annotations documented (4). Python and TypeScript SDKs, few required parameters (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.

## 5. Transparency & trust, 56 out of 100, up to 3.9 more on the total

Made of editorial 36, provenance 76.

Why it scored 56: Closed platform with terms from Galileo Technologies, Inc. Both SDKs are Apache-2.0 (15). The privacy policy was last updated on 1 November 2024, says data goes to servers in the US, allows de-identified customer data to be used for research and development and gives no retention periods. We found no DPA or subprocessor list (8). The rename to Splunk Agent Observability is dated 7 August 2026 in the release notes, but there's no timeline for api.galileo.ai, docs.galileo.ai or the SDKs (8). US data location stated, no subprocessors listed (5).

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: galileo.ai, registered 2020-05-05 (6 years) (11 of 15)
- Status page: not found (0 of 10)
- security.txt: not found (0 of 10)

## 6. Schema & documentation, 79 out of 100, up to 3.4 more on the total

Why it scored 79: OpenAPI 3.1 at api.galileo.ai/public/v2/openapi.json. The copy pinned in the Python SDK on 13 July has 184 paths and 244 operations (25). llms.txt on docs.galileo.ai and on the Splunk docs site, with Markdown pages (10). 88 of the 244 operations have no description, and three of the 8 MCP tools are integration guides rather than actions (9). Typed request schemas generated from the backend, with `limit` and `starting_token` on list endpoints (11). The spec declares only 200 and 422 responses, but the Splunk docs carry an error catalogue of 111 entries, each with a code, HTTP status, cause, fix and a retriable flag. Cookbooks give examples (11). Versioned `/v2` API and dated release notes, split between docs.galileo.ai (to 7 August) and the Splunk docs (15 September) (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. Maintenance & community, 74 out of 100, up to 2.3 more on the total

Why it scored 74: TypeScript SDK 2.3.2 on 2026-10-01 (30). TypeScript 2.3.0, 2.3.1 and 2.3.2 in September and Python 2.5.0, 2.5.1 and 2.6.0 in July (20). Dated release notes on two sites and Slack support on Pro, but the Python SDK has had no commit since 30 July and the product is mid-migration (8). Official Python and TypeScript SDKs, neither of which references the new Splunk SaaS hosts (10). CI tests, codecov and Dependabot. The Python `CHANGELOG.md` stops at v0.10.0 from May 2025 while releases have reached 2.6.0, and the TypeScript SDK shipped a breaking rename (`logstream` to `logStreamName`) in patch 2.1.2 (6).

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 new sign-ups at app.galileo.ai still create Galileo accounts or are moved to Splunk, and for how long api.galileo.ai will keep serving
- Whether a card is needed for the Free plan
- Whether Galileo or Splunk Agent Observability holds SOC 2 or similar certification. We found no claim on Galileo's pages and didn't search Splunk's corporate trust pages
- Pricing for the Splunk Observability Cloud SaaS version
- We didn't verify the Cisco acquisition announcement date in the listing's notable facts

## Weaknesses

- No status page, no published rate limits and no SLA
- Split between Galileo and Splunk since 7 August 2026, with two doc sites, two API hosts and no timeline for the old ones
- MCP server in preview with 8 tools, only `Get Signals` reads production data
- No security page, trust portal, security.txt or certification claim found, and the privacy policy dates from November 2024
- Python SDK quiet since 30 July and its CHANGELOG.md stuck at v0.10.0

## 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 which side the account lives on first. Pre-August Galileo accounts use api.galileo.ai, Splunk SaaS accounts use app.{realm}.observability.splunkcloud.com/ao/api/
- Send the key as `Splunk-AO-API-Key`. The current spec no longer lists `Galileo-API-Key`
- Page list endpoints with `limit` and `starting_token`
- Use the error catalogue's retriable flag to decide whether to retry. 429s carry no documented `Retry-After`
- Use the REST API to read traces. The MCP server mostly creates datasets and prompts

## What the review panel asked for

- an api.galileo.ai end date
- a current Python changelog
- describe every operation
- one doc site

## 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.