LangGraph by LangChain

# Fix list: LangGraph

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/langgraph, the October 2026 research run, assessed 1 October 2026. Grade BB, 70.6 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 LangGraph: 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. Security & auth, 60 out of 100, up to 7 more on the total

Why it scored 60: The library sends nothing according to the privacy page. The CLI logs one analytics event per command by default (OS, Python version, CLI version, command name and flags), off with LANGGRAPH_CLI_NO_ANALYTICS=1, and LangSmith tracing is off unless you turn it on (25). Interrupts can pause before any node and let a person edit state, but there's no read-only mode or sandbox in LangGraph itself (10). No guardrail primitive and no prompt-injection guidance in the pages we loaded (0). LangSmith tracing, opt-in (10). SECURITY.md routes reports to LangChain's two disclosure programmes on Intigriti, no bounty is mentioned, and eight GitHub advisories have been published with fixed versions (15). Framework reading, so SOC 2 isn't scored.

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.

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

Why it scored 75: Official packages on PyPI (Requires-Python >=3.10) and npm (node >=18) (20). The CI workflow passes on recent pull-request runs and CodeQL passes on main, but we didn't see a CI run on main itself (20). 416 open issues and 230 open pull requests (8). Five 1.2.x patch releases since July and a dated changelog, but we found no written versioning policy for LangGraph itself (12). 1.2.12, classed 5 - Production/Stable (15).

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. Payments & pricing, 60 out of 100, up to 5 more on the total

Why it scored 60: No payment protocol (0). Scored on LangSmith, the hosted option, which publishes per-unit prices without a login (1 LSU = $1, runtime compute at 0.0675 LSU a vCPU-hour, Plus at $39 a seat a month) (20). The MIT package installs with no card (20) and no account, and runs any model including local ones (20).

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, 70 out of 100, up to 4.9 more on the total

Why it scored 70: No MCP client in LangGraph. It comes from LangChain's langchain.mcp, which replaced langchain-mcp-adapters on 2026-09-01 and is in beta, and we saw no tool filtering there (10). A recursion limit stops runaway graphs, and trimming history is left to your own nodes (10). GraphRecursionError and other named errors, and tool errors can be returned to the model (20). Per-node retry policies and checkpointed resume (20). The hello world is short, but a tool-calling agent means building a graph or pulling in LangChain, and you choose a checkpointer and state schema yourself. Python and TypeScript (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.

## 5. Schema & documentation, 89 out of 100, up to 1.8 more on the total

Why it scored 89: A typed graph API with a reference site (25). llms.txt at docs.langchain.com, per the listing's earlier check (10). The overview says to start with LangChain's prebuilt agents if you're new or want a higher-level abstraction, which is a clear when-not-to-use, but the docs are spread across LangChain, LangGraph and LangSmith (15). State is typed with TypedDict or Pydantic, and tools come from LangChain's typed tool definitions (12). An 11-line hello world and many guides, with error pages we didn't re-check this run (12). Dated changelog (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 89, provenance 68.

Why it scored 79: MIT (30). The data-storage page says what the CLI sends, that langgraph dev keeps data in a local .langgraph_api folder, that nothing else leaves the machine unless tracing is on, and that langgraph up checks a licence key (25). The changelog dates deprecations, such as the MCP adapters on 2026-09-01, but we found no written support window (14). CLI analytics and LangSmith tracing are both disclosed with opt-outs (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):

- Domain age: langchain.com, registered 2019-12-03 (6 years) (11 of 15)
- Status page: not found (0 of 10)
- security.txt: not found (0 of 10)

## 7. Maintenance & community, 90 out of 100, up to 0.9 more on the total

Why it scored 90: 1.2.12 on 2026-09-21 (30). Five releases since 2026-07-03 (1.2.8 to 1.2.12) (20). 416 open issues and 230 open pull requests, with automation that tags outside issues and requires an issue link on pull requests; we couldn't see reply times (15). langgraph 1.2.12 on PyPI and @langchain/langgraph 1.4.18 on npm (15). CI and CodeQL pass (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.

## Deductions

Each comes off the total. A fixed and documented problem counts for less at the next check.

- 2025-10-29 to 2025-12-09. Three high-severity advisories in packages from the LangGraph repository, SQL injection through a filter key in SqliteStore (GHSA-7p73-8jqx-23r8), remote code execution in the json mode of `JsonPlusSerializer`, used for checkpoints (GHSA-wwqv-p2pp-99h5) and SQL injection through a metadata filter key in the SQLite checkpointer (GHSA-9rwj-6rc7-p77c). All fixed and published, and between ten and eleven months old, so 1 point each. Five moderate advisories in 2026 weren't deducted. https://github.com/langchain-ai/langgraph/security

## 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.

- We couldn't load langchain.com's terms and privacy pages this run, so the provenance block's blank terms and privacy fields are unchanged
- We didn't confirm whether the langchain-mcp-adapters README now carries a deprecation notice
- Retry policies, the recursion limit and the error pages weren't re-checked this run
- We found no bug bounty for LangChain's disclosure programmes, but didn't open the Intigriti pages

## Weaknesses

- No MCP client of its own. LangChain's langchain.mcp is in beta
- More code than the others for a plain tool-calling agent
- No guardrail primitive or sandbox in LangGraph itself
- 416 open issues and 230 open pull requests
- The CLI sends an analytics event per command by default

## 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 a persistent checkpointer in production, not the in-memory one
- Move from langchain-mcp-adapters to langchain.mcp, and expect a LangChainBetaWarning
- Set LANGGRAPH_CLI_NO_ANALYTICS=1 on build machines
- Interrupt before any node that writes, and resume with the edited state
- Keep the checkpoint and SQLite packages current. Each had a high-severity advisory in late 2025

## What the review panel asked for

- a written versioning policy
- Mark the adapters README deprecated
- Put MCP and graph docs on one 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.