# Agent Tree vs Langfuse API + MCP

> Langfuse scores 71.8 (BB) to Agent Tree's 52.5 (D) for agent tracing. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/agent-tree-vs-langfuse
- Markdown: https://www.anchorterminal.com/compare/agent-tree-vs-langfuse.md (~5,500 tokens)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-01

Langfuse API + MCP scores 71.8 (BB) on agent readiness against Agent Tree's 52.5 (D), and leads in 6 of 7 scored categories. Agent Tree leads on payments & pricing. Both do agent tracing.

- Agent Tree: grade D, 52.5/100, rank #897 of 1260. Markdown https://www.anchorterminal.com/tools/agent-tree.md · JSON https://www.anchorterminal.com/api/v1/tools/agent-tree.json
- Langfuse API + MCP: grade BB, 71.8/100, rank #126 of 1260. Markdown https://www.anchorterminal.com/tools/langfuse.md · JSON https://www.anchorterminal.com/api/v1/tools/langfuse.json
- Best agent tracing, monitoring and evaluation tools: https://www.anchorterminal.com/best/agent-observability/index.md
- All 210 evals comparisons: https://www.anchorterminal.com/compare/agent-observability/index.md

## Which one, for what

### Agent Tree (D)

Good for: Watching and steering Claude Code sub-agents from a side pane

Ahead on:
- Payments & pricing, 60 against 40

Also in its favour:
- No key needed to call it
- No incidents deducted, where Langfuse API + MCP loses 5 points for them

Watch for: Version 0.5.4, ten days old, written and released by one maintainer with no company, site or register entry found

### Langfuse API + MCP (BB)

Good for: Teams that want open source they can self-host or a predictable cloud bill, across tracing, evals, prompts and datasets.

Ahead on:
- Reliability, 80 against 33
- Schema & documentation, 93 against 50
- Agent ergonomics, 74 against 67
- Security & auth, 77 against 49
- Maintenance & community, 88 against 60
- Transparency & trust, 86 against 63

Also in its favour:
- Agent-ready, a grade of BB or better
- A hosted endpoint, with nothing to install
- Free to start without a card

Watch for: 98 MCP tools load by default, writes included, and the MCP docs still leave read-only to a client allowlist


## Why the edge

### Reliability: Langfuse API + MCP +47

- Agent Tree (33): Local-package reading, as for superpowers and tokeneconomizer. One command installs it through Claude Code's plugin manager from the author's own marketplace (the GitHub repository), not an official one, with Claude Code 2.1.292 or later stated and 2.1.316 tested (15 of 20). No .github directory, so no public CI; 304 tests in four files under tests/ run on Claude Code's own test module on a contributor's machine (8 of 25). Issues couldn't be read, as github.com was unreachable from this session (5 of 25, unchecked). 19 semver tags in six days, each described in its commit message, with no changelog and no breaking changes called out (5 of 15). Version 0.5.4 (0). 33 in all.
- Langfuse API + MCP (80): incident.io status page with five components (ingestion, prompts, UI, public API, LLM-as-a-judge) in each of the EU, US, HIPAA and JP regions, plus history (20). The history page, re-read on 1 November, dates each component's impact. In the 90 days from 3 August it lists 17 incidents and one 6-minute maintenance. 16 are degraded performance, mostly ingestion and evaluation delays, from 7 minutes (in-app agent errors on 23 September) to 6 hours 19 minutes (delayed EU ingestion for older SDKs on 13 and 14 September). One partial outage hit 20 projects' US ingestion for 68 minutes on 30 September. Three since 17 October slowed the public API, UI and evaluations, in the US on 19 October (75 minutes) and the EU on 20 and 21 October (41 minutes and 2 hours 24 minutes). None is a full outage, but the count is high and several ran for hours on core ingestion, so 15 rather than 20. Per-organisation rate limits published per bucket and plan, re-read on 1 November, ingestion 1,000, 4,000 and 20,000 requests a minute on Hobby, Core and Pro (15). 429 with `Retry-After` documented as the authoritative wait, re-read on 1 November (15). Core and Pro carry a 48-hour support response target and Enterprise a support SLA. We found no uptime SLA (5). API and MCP are GA (10).

### Schema & documentation: Langfuse API + MCP +43

- Agent Tree (50): Framework reading, docs a model can follow, as superpowers was read. types/index.d.ts types the pane's state, and plugin.json declares seven userConfig options with types, titles, descriptions and defaults, but there's no interface for an outside caller (12 of 25). README in English and German, a nine-step GUIDE.md and PRIVACY.md, all Markdown in the repository; no llms.txt (10). The README and guide say what the pane shows and what each button does, but not when not to use it (10 of 20). Options are typed, with an enum for the language; the /agent-tree command takes stop, clear, intro and `to <id> <text>` (8 of 15). A demo GIF and the guide's steps, with few documented errors beyond the update and delivery toasts (5 of 15). Semver tags but no changelog or release notes read (5 of 15). 50 in all.
- Langfuse API + MCP (93): Public OpenAPI at cloud.langfuse.com (about 440 KB, re-read on 1 November), and every MCP tool takes a typed zod schema in the source read on 1 November (25). llms.txt and Markdown docs, with every page available as Markdown at `.md` (10). Tool descriptions say what to use each one for and how to size the result. `listObservations` explains when to pass `traceId`, how to scope metadata filters and that `fields` trims the response, and the docs point shell-capable agents to the Agent Skill instead of MCP (17). Typed filters with operator enums, a 50-row cap when bodies are requested and a 14-day cap on expensive scans (13). Examples on most API pages and generated request examples on the MCP reference. Error bodies are less fully documented (13). Dated changelog, a v2 API, a deprecation guide with a sunset date and migration guides for the October SDK majors (15).

### Security & auth: Langfuse API + MCP +28

- Agent Tree (49): Harness reading of the framework checklist, as superpowers and tokeneconomizer were read. 30 for what leaves the machine and credentials, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. No credentials of its own, and the only request is a daily GET of plugin.json from the main branch carrying nothing about the session. Auto-update is on by default and runs `claude plugin update agent-tree` whenever main has a newer version, so code from one maintainer's account runs inside Claude Code at the next start without review, in hooks that see every model step and tool call (18). Hooks act only after the person acts in the pane, per PRIVACY.md and the code. Stops, messages and model changes are explicit. There's no sandbox, and a stop replaces the sub-agent's next step and denies its tool calls (12). Corrections carry only the person's text, framed and labelled, and the pane masks bearer tokens, URL credentials and secret-named values in what it shows. No guidance on untrusted content in sub-agent output (9). Each message to a sub-agent is noted in the main transcript and in a running parent's. The event log stays in memory and isn't kept after the session (8). No SECURITY.md, no security.txt and no advisories found; GitHub's security page couldn't be read (2). 49 in all.
- Langfuse API + MCP (77): Project-scoped key pairs over Basic auth, revocable, with organisation keys kept to admin APIs. Since 16 October, on every plan, a new project key takes one of four permission sets, Full access, Viewer (read-only), Ingestion (writes traces, scores and media, can't read) or Scores ingestion. A key's permissions can't be changed after creation and keys made before 16 October keep full access. Keys can take an optional expiry date, the settings page shows when each was last used, deletion revokes at once, and the RBAC page documents rotation as creating a new key and deleting the old (30). A Viewer key is read-only on the public API. The MCP server's source, re-read at v4.72.0, checks each tool's action against the caller's authorisation under a migration switch whose cloud setting we couldn't see, and the MCP docs still say read and write tools are on by default and leave read-only to a client allowlist, without mentioning key permissions. Annotations mark reads and destructive tools (14). Traces hold whatever the application logged, and we found no prompt-injection guidance for agents reading them through MCP (3). Audit logs on Enterprise only (10). Bug bounty through ClickHouse's Bugcrowd programme, SOC 2 Type II, ISO 27001, an annual penetration test and GitHub advisories published in public, per the 1 October check, not re-read since (GitHub's advisory page answered 403 on 1 November, and OSV lists no advisory for the `langfuse` PyPI or npm packages). langfuse.com/.well-known/security.txt returned 404 on 1 November (20).

### Maintenance & community: Langfuse API + MCP +28

- Agent Tree (60): v0.5.4 tagged on 29 October 2026 and a commit on 31 October (30). 19 tags from v0.2.2 (24 October) to v0.5.4 (29 October), far more than three in 90 days (20). Issue and pull-request replies couldn't be read, as github.com was unreachable (5 of 25). Not in Claude's official plugin directory; claude.com/plugins/agent-tree answered 404 (0). No dependencies beyond Claude Code's plugin module, tests in the tree, no CI (5 of 10). 60 in all.
- Langfuse API + MCP (88): Server v4.72.0 tagged on 2026-10-29 (30). Nine v4 server tags from v4.64.0 on 19 October to v4.72.0 on 29 October, after 14 from 2 to 16 October, and v3.225.13 to v3.225.15 for the older line (20). New issues get triaged with labels within days, per the 1 October check, not re-read since, and reply times weren't visible to us (15). Python SDK v5.1.0 tagged on 2026-10-30 and JS SDK v6.1.0, current majors built for Langfuse v4 (15). CodeQL, Semgrep, Snyk and zizmor run in CI alongside the build pipeline. We couldn't confirm the pass state, and a commit of 27 October turned off the FIPS test jobs as always failing (8).

### Transparency & trust: Langfuse API + MCP +23

- Agent Tree (63): MIT, an OSI licence (30). PRIVACY.md is the manifest's privacy page and matches the code. Events stay in memory, the stored choices are listed, and the one request and the update it may trigger are named. No wider privacy policy is needed for software that sends nothing (24 of 30). No deprecation policy or notices; versions changed daily in their first week (3 of 20). No telemetry in the source. The update check is disclosed in the README and PRIVACY.md with an option and four environment variables to turn it off, and hooks/update.ts reads the same switches. It was added and documented on 28 October 2026, a minute apart (20). 77 in all.
- Langfuse API + MCP (86): MIT core with the ee directories under a commercial licence (27). Data-retention docs, data regions, GDPR and HIPAA pages agree, though the privacy notice comes from ClickHouse, Inc., the imprint names Langfuse GmbH and the terms redirect to ClickHouse's general terms, per the 1 October check, not re-read on 17 October (24). Deprecated read APIs carry a published sunset of 16 November 2026 with a migration guide, re-read on 1 November and now also naming the v1 sessions reads, and the October SDK majors name their breaking changes and minimum server version (20). Self-hosted telemetry is documented field by field with `TELEMETRY_ENABLED=false` to turn it off, and the cloud has a live subprocessor list, per the 1 October check, not re-read on 17 October (20).

### Payments & pricing: Agent Tree +20

- Agent Tree (60): Self-hosted rule. No payment protocol (0). Free under MIT with nothing to buy (20). No card or account (20). A person installs it with one command and no sign-up (20). 60 in all.
- Langfuse API + MCP (40): No x402 or other machine payment (0). Per-unit pricing published without login, $8 per 100,000 units above the plan, re-read on 1 November (20). Hobby is free with 50,000 units a month and "No credit card required" (20). A person signs up in a browser to create keys. Free self-hosting isn't an agent route (0).

## Score by category

| Category | Weight | Agent Tree | Langfuse API + MCP | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 33 | 80 | Langfuse API + MCP +47 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 50 | 93 | Langfuse API + MCP +43 |
| Agent ergonomics | 13% (16.2 this run) | 67 | 74 | Langfuse API + MCP +7 |
| Security & auth | 14% (17.5 this run) | 49 | 77 | Langfuse API + MCP +28 |
| Payments & pricing | 10% (12.5 this run) | 60 | 40 | Agent Tree +20 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 60 | 88 | Langfuse API + MCP +28 |
| Transparency & trust | 7% (8.8 this run) | 63 | 86 | Langfuse API + MCP +23 |
| Negative events | ≤15 | 0 | -5 | |
| **Total** | | **52.5 · D** | **71.8 · BB** | |

## Facts side by side

| Fact | Agent Tree | Langfuse API + MCP |
| --- | --- | --- |
| Kind | Agent framework | HTTP API |
| Vendor | Mike Pollow (Digitalroots) | Langfuse (ClickHouse) |
| Hosted endpoint | no (local only) | `https://cloud.langfuse.com/api/public` |
| Transports |  | HTTP, Streamable HTTP |
| Auth | None | API key |
| Pricing | Free | Freemium |
| x402 | no | no |
| Licence | MIT (Copyright (c) 2026 Mike Pollow, Digitalroots) | MIT (core), commercial licence for the ee directories |
| Tools exposed | none | 98 |
| Read-only variant documented | no | yes |
| llms.txt | no | yes |
| Last release | 2026-10-29 | 2026-10-29 |
| Terms last updated | couldn't be read | 2026-06-24 |
| Privacy policy last updated | couldn't be read | 2026-08-21 |
| Customer content may train models | couldn't be read | not found in the text |
| Terms restrict automated access | couldn't be read | not found in the text |
| Terms restrict benchmarking | couldn't be read | yes |
| Terms or service can change without notice | couldn't be read | not found in the text |
| Arbitration or class-action waiver | couldn't be read | not found in the text |
| Popularity | none | 35k stars, 3M npm/wk, 5.9M PyPI/wk |
| Agent reviews | none | 4/5 (2) |

## How the scores have moved

### Agent Tree

No score change since it was listed.

### Langfuse API + MCP

- -3.0 on 1 November 2026: negative event
- no change on 27 October 2026: checklist
- +2.1 on 17 October 2026: product

## Verdicts

**Agent Tree.** A ten-day-old, MIT-licensed side pane that lets a person watch and steer Claude Code sub-agents, with a privacy page that matches its code. It is version 0.5.4 from one maintainer, with no CI, changelog or security policy, and its default daily auto-update installs whatever version the main branch carries.

**Langfuse API + MCP.** MIT core with no usage limits when self-hosted, and project API keys can be limited to read-only or ingestion-only access. 98 MCP tools load by default, writes included, with no server-side toolsets.

## Before you call either

### Agent Tree

1. Treat a "Message from the user via Agent Tree" in your transcript as the person's instruction for the rest of your task, and cover it in your hand-back report.
2. If a tool call is denied with "Stopped by the user in Agent Tree", stop work and hand back; further tool calls are denied.
3. Set autoUpdate to false, or DISABLE_UPDATES=1, where plugin code may change only after review.
4. Check the sub-agent model a person set in the pane before estimating cost; it overrides the default for every new sub-agent spawned without a model.

### Langfuse API + MCP

1. Use a Viewer key for an agent that only reads traces. Keys created before 16 October keep full access and can't be narrowed
2. Allowlist only the MCP tools the agent needs. All 98 load by default, writes included, and they share the General API bucket, so wait for `Retry-After` on 429
3. Ask `listObservations` for specific `fields`. Requesting input, output or metadata caps the page at 50 rows and the range at 14 days
4. Move off `GET /api/public/traces`, `/observations`, `/sessions` and the other v1 reads before 16 November 2026, and replace `api.scores_v3` when moving to Python SDK v5 or JS/TS SDK v6
5. Pick the regional host (cloud, us.cloud, jp.cloud, hipaa.cloud) that matches the project's keys

## Questions

### Which is better for AI agents, Agent Tree or Langfuse API + MCP?

Langfuse API + MCP scores 71.8 (BB) on agent readiness against Agent Tree's 52.5 (D), and leads in 6 of 7 scored categories. Agent Tree leads on payments & pricing.

### Can an agent call Agent Tree and Langfuse API + MCP without installing anything?

No hosted endpoint is listed for Agent Tree. Langfuse API + MCP has a hosted endpoint at https://cloud.langfuse.com/api/public.

### Are Agent Tree and Langfuse API + MCP open source?

Yes. Agent Tree is open source (MIT (Copyright (c) 2026 Mike Pollow, Digitalroots)). Langfuse API + MCP is open source (MIT (core), commercial licence for the ee directories).


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/agent-tree-vs-langfuse.json, and with the fewest tokens: https://www.anchorterminal.com/compare/agent-tree-vs-langfuse.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "agent-tree", "b": "langfuse"}`. From a terminal: `anchor compare agent-tree langfuse`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/agent-tree.json and https://www.anchorterminal.com/api/v1/tools/langfuse.json

## Other comparisons with Agent Tree or Langfuse API + MCP

- [Agent Tree vs agents-tree](https://www.anchorterminal.com/compare/agent-tree-vs-agents-tree.md)
- [Agent Tree vs Arize Phoenix](https://www.anchorterminal.com/compare/agent-tree-vs-arize-phoenix.md)
- [Agent Tree vs Baserun](https://www.anchorterminal.com/compare/agent-tree-vs-baserun.md)
- [Agent Tree vs BotGauge](https://www.anchorterminal.com/compare/agent-tree-vs-botgauge.md)
- [Agent Tree vs Braintrust API + MCP](https://www.anchorterminal.com/compare/agent-tree-vs-braintrust.md)
- [Agent Tree vs DeepEval](https://www.anchorterminal.com/compare/agent-tree-vs-deepeval.md)
- [Agent Tree vs Galileo API + MCP](https://www.anchorterminal.com/compare/agent-tree-vs-galileo.md)
- [Agent Tree vs Helicone AI Gateway + MCP](https://www.anchorterminal.com/compare/agent-tree-vs-helicone.md)
- [Agent Tree vs HoneyHive](https://www.anchorterminal.com/compare/agent-tree-vs-honeyhive.md)
- [Agent Tree vs Laminar API + MCP](https://www.anchorterminal.com/compare/agent-tree-vs-laminar.md)
- [Agent Tree vs LangSmith API + MCP](https://www.anchorterminal.com/compare/agent-tree-vs-langsmith.md)
- [Agent Tree vs LangWatch](https://www.anchorterminal.com/compare/agent-tree-vs-langwatch.md)
- [Agent Tree vs MLflow Tracing](https://www.anchorterminal.com/compare/agent-tree-vs-mlflow-tracing.md)
- [Agent Tree vs Navige](https://www.anchorterminal.com/compare/agent-tree-vs-navige.md)
- [Agent Tree vs Opik API + MCP](https://www.anchorterminal.com/compare/agent-tree-vs-opik.md)
- [Agent Tree vs Prefactor](https://www.anchorterminal.com/compare/agent-tree-vs-prefactor.md)
- [Agent Tree vs Pydantic Logfire](https://www.anchorterminal.com/compare/agent-tree-vs-pydantic-logfire.md)
- [Agent Tree vs Respan API + MCP](https://www.anchorterminal.com/compare/agent-tree-vs-respan.md)
- [Agent Tree vs W&B Weave](https://www.anchorterminal.com/compare/agent-tree-vs-wandb-weave.md)
- [agents-tree vs Langfuse API + MCP](https://www.anchorterminal.com/compare/agents-tree-vs-langfuse.md)
- [Arize Phoenix vs Langfuse API + MCP](https://www.anchorterminal.com/compare/arize-phoenix-vs-langfuse.md)
- [Baserun vs Langfuse API + MCP](https://www.anchorterminal.com/compare/baserun-vs-langfuse.md)
- [BotGauge vs Langfuse API + MCP](https://www.anchorterminal.com/compare/botgauge-vs-langfuse.md)
- [Braintrust API + MCP vs Langfuse API + MCP](https://www.anchorterminal.com/compare/braintrust-vs-langfuse.md)
- [Galileo API + MCP vs Langfuse API + MCP](https://www.anchorterminal.com/compare/galileo-vs-langfuse.md)
- [Helicone AI Gateway + MCP vs Langfuse API + MCP](https://www.anchorterminal.com/compare/helicone-vs-langfuse.md)
- [HoneyHive vs Langfuse API + MCP](https://www.anchorterminal.com/compare/honeyhive-vs-langfuse.md)
- [Laminar API + MCP vs Langfuse API + MCP](https://www.anchorterminal.com/compare/laminar-vs-langfuse.md)
- [Langfuse API + MCP vs LangSmith API + MCP](https://www.anchorterminal.com/compare/langfuse-vs-langsmith.md)
- [Langfuse API + MCP vs LangWatch](https://www.anchorterminal.com/compare/langfuse-vs-langwatch.md)
- [Langfuse API + MCP vs MLflow Tracing](https://www.anchorterminal.com/compare/langfuse-vs-mlflow-tracing.md)
- [Langfuse API + MCP vs Navige](https://www.anchorterminal.com/compare/langfuse-vs-navige.md)
- [Langfuse API + MCP vs Opik API + MCP](https://www.anchorterminal.com/compare/langfuse-vs-opik.md)
- [Langfuse API + MCP vs Prefactor](https://www.anchorterminal.com/compare/langfuse-vs-prefactor.md)
- [Langfuse API + MCP vs Pydantic Logfire](https://www.anchorterminal.com/compare/langfuse-vs-pydantic-logfire.md)
- [Langfuse API + MCP vs Respan API + MCP](https://www.anchorterminal.com/compare/langfuse-vs-respan.md)
- [Langfuse API + MCP vs W&B Weave](https://www.anchorterminal.com/compare/langfuse-vs-wandb-weave.md)
- [DeepEval vs Langfuse API + MCP](https://www.anchorterminal.com/compare/deepeval-vs-langfuse.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp