LanceDB by LanceDB

# Fix list: LanceDB

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/lancedb, the October 2026 research run, assessed 1 October 2026. Grade B, 65.4 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 LanceDB: 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). The only paid product, Enterprise, sits behind a contact form (0). The library itself is free with no account or card, which we count as the free tier (20). Getting the paid product needs a sales conversation (0). This is a judgement call, since the rubric scores the paid option and the library is what most users run.

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. Security & auth, 44 out of 100, up to 9.8 more on the total

Why it scored 44: The library has no auth of its own and uses the host's object-store credentials. Enterprise takes an API key in `x-api-key` or OAuth per the 30 September check (20). Least privilege depends on read-only bucket credentials. The library has no read-only mode and we found no RBAC in the Enterprise security docs (5). Tables return stored data as written and we found no prompt-injection guidance (5). No audit log found (0). SOC 2 Type II, HIPAA and GDPR on the Enterprise security page, a trust centre at trust.lancedb.com and a valid security.txt per the 30 September check, but no SECURITY.md and no advisories ever published (14).

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. Reliability, 75 out of 100, up to 5 more on the total

Why it scored 75: Scored as a local package. Official packages on PyPI, npm and crates.io, with Python 3.10 or later and Node 22 or later stated (20). Public CI with Python, Node, Rust and Java test workflows, and the ten most recent Python runs on main all passed (25). 493 open issues, but the newest bug reports are mostly filed and labelled by maintainers themselves, several within a day of each other in late September (15). Releases follow semver for 0.x, breaking changes bump the minor version, and GitHub release notes have Breaking Changes and Deprecations sections (15). Still 0.x and not declared stable (0).

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.

## 4. Agent ergonomics, 74 out of 100, up to 4.2 more on the total

Why it scored 74: No official MCP server, only a 3-tool reference example, so an agent needs code or its own wrapper (15). `select()`, `limit()`, `offset()`, `where()` and query types to size and filter results (20). Errors are typed exceptions without documented codes (12). `merge_insert` gives upserts, and writes create new table versions you can roll back to, but there are no tool annotations to read (12). Python, TypeScript, Rust and Java clients, embedded with sensible defaults and nothing to deploy (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. Schema & documentation, 81 out of 100, up to 3.1 more on the total

Why it scored 81: Typed Python, TypeScript and Rust APIs, and the Lance REST Namespace has an OpenAPI 3.1.1 spec in lance-format/lance-namespace. The docs' own Enterprise OpenAPI link still returned 404 on 1 October (20 of 25). llms.txt indexes 100 or more Markdown pages (10). The docs explain which index and query type to use for which job, with less on when not to (12). Typed query builders and schemas, but filters are SQL strings (13). Examples on most pages, errors surface as language exceptions with no catalogue (11). Dated GitHub releases with breaking-change and deprecation sections (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. Transparency & trust, 79 out of 100, up to 1.8 more on the total

Made of editorial 75, provenance 82.

Why it scored 79: Apache-2.0 (30). Terms and privacy are PDFs on a HubSpot file host. The terms name the vendor only as Company, the privacy PDF names LanceDB Systems, Inc., and the Enterprise docs say customer data stays in the customer's account (15). Release notes carry a Deprecations section and breaking changes bump the minor version, but there's no notice period (12). No telemetry module in the open-source library source, and the Enterprise docs limit telemetry to system health (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.

Provenance checks not met in full (half of this category, computed from checked facts):

- Domain age: lancedb.com, registered 2023-03-18 (3 years) (7 of 15)
- Status page: not found (0 of 10)

## 7. Maintenance & community, 93 out of 100, up to 0.6 more on the total

Why it scored 93: v0.39.0 on 17 September 2026 (30). python-v0.36.0, v0.37.1, v0.38.0 and v0.39.0 since late July, with v0.40.0 betas through 30 September (20). Maintainers file and label bugs themselves and merged fixes on 1 October, though 493 issues are open (18). Python, TypeScript, Rust and Java clients ship from one version tag (15). Passing CI, Dependabot and cargo-deny (10).

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 LanceDB Cloud at cloud.lancedb.com still takes self-serve sign-ups. The docs only cover OSS and Enterprise, and an open issue asks about Cloud billing
- Whether the Enterprise REST API matches the Lance REST Namespace OpenAPI spec in full, since the docs' own spec link is a 404
- unchecked: whether Enterprise has audit logs or read-only roles

## Weaknesses

- No self-serve hosted API. Enterprise is sold through a contact form
- No official MCP server, only a 3-tool reference example
- The docs' OpenAPI link for the Enterprise REST API returns 404
- Still 0.x, and Node 22 or later is now required
- No SECURITY.md in the repository

## 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 it through the Python or TypeScript library. There's no public endpoint an agent can call without an Enterprise deployment
- Build an FTS index before calling `query_type="hybrid"`, or hybrid search has no keyword side
- Call `optimize()` after many small writes, since each write adds a new file version
- Use `select()` to drop the vector column from results unless the task needs it
- On object storage, set a read consistency interval if several processes write the same table

## What the review panel asked for

- a stated notice period
- a 1.0 line
- Publish an Enterprise rate card
- Confirm Cloud sign-up status

## 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.