# goose vs Traycer

> goose scores 71.3 (BB) to Traycer's 57 (C) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/goose-vs-traycer
- Markdown: https://www.anchorterminal.com/compare/goose-vs-traycer.md (~5,700 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: 2026-11-07

goose scores 71.3 (BB) on agent readiness against Traycer's 57 (C), and leads in every scored category. Both do agent harnesses.

- goose: grade BB, 71.3/100, rank #166 of 1510. Markdown https://www.anchorterminal.com/tools/goose.md · JSON https://www.anchorterminal.com/api/v1/tools/goose.json
- Traycer: grade C, 57/100, rank #816 of 1510. Markdown https://www.anchorterminal.com/tools/traycer.md · JSON https://www.anchorterminal.com/api/v1/tools/traycer.json
- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md
- All 1500 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md

## Which one, for what

### goose (BB)

Good for: People and pipelines that want one agent across many model providers or local models, with recipes for repeatable jobs and a desktop app for non-engineers.

Ahead on:
- Reliability, 77 against 65
- Schema & documentation, 81 against 65
- Agent ergonomics, 82 against 65
- Security & auth, 77 against 42
- Payments & pricing, 60 against 30
- Maintenance & community, 86 against 75
- Transparency & trust, 67 against 60

Also in its favour:
- Agent-ready, a grade of BB or better
- Free to start without a card

Watch for: Autonomous mode, which approves every tool call, is the default

### Traycer (C)

Good for: Teams who want several coding agents working together with shared context and boards.

Also in its favour:
- No incidents deducted, where goose loses 5 points for them

Watch for: Privacy Mode is opt-in for individuals; with it off, prompts may be logged


## Why the edge

### Security & auth: goose +35

- goose (77): Harness reading of the framework checklist, used for all five harnesses in this batch. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. Usage data is off until the user agrees on first use, and the docs list what's collected and what isn't (30). Four modes (autonomous, smart approval, manual approval, chat only), per-tool always, ask or never rules, and an extension allowlist fetched from `GOOSE_ALLOWLIST`, which from 1.57.0 must be HTTPS and blocks installs when the policy can't be read, but autonomous is the default (the first-run prompt for the mode still preselects Auto in 1.57.0) and there's no sandbox, with the docs pointing to a VM or container (11). Pattern and optional ML prompt-injection detection and an adversary reviewer for shell calls, both off until turned on, plus a prompt-injection caution in SECURITY.md (11). Session logs, a diagnostics report and a Langfuse tracing guide (12). SECURITY.md with GitHub private reporting and an AAIF governance contact, one advisory published with a CVE, and a Scorecard workflow. A second CVE, CVE-2026-109561 (low, Manual Approval bypassed by persisted read-only annotations after Smart Approval, fixed in 1.44.0), was published by NVD on 12 October from a third party, with no goose advisory of its own. No bug bounty, and goose-docs.ai/.well-known/security.txt returned 404 on 6 and 17 October and 1 November (13).
- Traycer (42): Harness reading. Code is processed in memory and not used for training, but Privacy Mode is opt-in for individuals, prompts may be logged with it off, and Sentry and PostHog 'may be enabled in release builds' (10 of 30). No approval model described in the README (8 of 20). No prompt-injection guidance (5). No audit log found (5). SECURITY.md, CodeQL, Scorecard and secret scanning (14 of 20). 10 + 8 + 5 + 5 + 14 = 42.

### Payments & pricing: goose +30

- goose (60): No payment protocol (0). Free and Apache-2.0 with nothing to buy, so 20, 20 and 20 on the last three lines. It runs local models, including built-in local inference, with no signup.
- Traycer (30): Scored on the paid option, Traycer's own inference subscription, whose price wasn't read (0 of 20). No protocol (0). Bring-your-own-agent use is free (20). Accounts for sync and teams weren't checked, half (10). 0 + 0 + 20 + 10 = 30.

### Agent ergonomics: goose +17

- goose (82): Harness reading of the framework line, scored on what an agent or pipeline driving it has to supply. The built-in extensions are few, and Code Mode lets the model find MCP tools through code instead of loading every definition (23). `--max-turns` (default 1000), `GOOSE_MAX_TOKENS` and automatic context compaction, though 1000 turns is a high default for an unattended run (16). `goose run --output-format json` or `stream-json` for scripts (15). Recipes can retry with success checks and an `on_failure` command, and sessions resume (17). A Rust core with Python and Java SDK builds, and one command runs a task, but a provider has to be configured first and the default mode approves everything (11).
- Traycer (65): Harness reading. Model switching within an agent, agent-to-agent loops, a CLI and cross-device sync (65).

### Schema & documentation: goose +16

- goose (81): Recipes have a documented schema with typed parameters and a `response` JSON Schema for structured output, and config and environment variables are documented in tables, but we found no OpenAPI spec for the goose server (18). llms.txt at goose-docs.ai, which now covers goose and the goose Development Kit (10). Permission modes come with a best-for column and the security pages say what each guard catches and misses (15). Recipe parameters take types and requirement levels, and retries take typed success checks (12). Many tutorials, a headless guide that tells scripts to check exit codes, and a known-issues page (13). Dated, written notes on every GitHub release, with no changelog file (13).
- Traycer (65): Harness reading. Mintlify docs, a protocol package and a CLI (65).

### Reliability: goose +12

- goose (77): Read as a local package, which is how the 1 October dossier read it. Desktop builds and a CLI for macOS, Linux and Windows (a Windows NSIS installer from 1.56.0), Homebrew casks, a download script on GitHub releases, an npm package that installs the binary (@aaif/goose-acp) and a GHCR image, with Rust 1.94.1 as the minimum for source builds (20). A CI workflow runs on every push to main, with cargo-deny, cargo-machete, MCP and tool-call conformance and an OpenSSF Scorecard job beside it. The Actions page loaded on 1 October showed only passing runs from March 2026, and GitHub pages refused our requests on 6 and 17 October and 1 November, so the current state is unconfirmed (18). 266 to 271 open issues on 1 October, many from that week with no reply, including open reports that the default mode approves every tool call (#12567) and that schedules can overwrite each other (#12613), per the 1 October check, not re-read since (15). Weekly minor releases with notes written by a release-notes workflow whose sections are `Features`, `Bug Fixes`, `Improvements` and `Documentation`, with no breaking-change section. 1.55.0 dropped background subagents (`delegate(..., async: true)` and `GOOSE_MAX_BACKGROUND_TASKS`) and 1.57.0 dropped the developer tools that delegated file reads and terminal commands to an ACP editor, each edited out of the code and docs with no earlier notice (9). 1.57, stable (15).
- Traycer (65): Local software. Builds for macOS, Linux and Windows, and package-manager publishing workflows (20). test.yml, CodeQL, OpenSSF Scorecard and secret scanning run on the repository; pass state not read (15). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). CHANGELOG.md (15). Host 1.5.3 (15). 20 + 15 + 0 + 15 + 15 = 65.

### Maintenance & community: goose +11

- goose (86): v1.57.0 tagged on 27 October 2026, after v1.56.0 on 22 October (30). 13 releases in the 90 days from 3 August, 1.46.0 (11 August) to 1.57.0, about one a week, plus GDK alpha tags (20). Issues move through a public board with Inbox and Ready columns and some new reports get a label within a day, but many of the week's reports had no reply on 1 October, and pull requests that don't implement a Ready issue are closed, per the 1 October check, not re-read since (15). Desktop, CLI, npm and GHCR builds ship from the same tag, and Python and Java SDK builds run in CI (13). cargo-deny, cargo-machete, Dependabot and Scorecard workflows, every GitHub Action pinned to a commit SHA since 29 September, and jsonwebtoken removed on 26 October to stop ignoring its cargo-deny advisories, with the current CI state unconfirmed (8).
- Traycer (75): Commits on 6 November 2026 and host 1.5.3 (30). More than three releases in 90 days (20). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). Current apps and CLI packages (15). CI with tests (10). 30 + 20 + 0 + 15 + 10 = 75.

## Score by category

| Category | Weight | goose | Traycer | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 77 | 65 | goose +12 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 81 | 65 | goose +16 |
| Agent ergonomics | 13% (16.2 this run) | 82 | 65 | goose +17 |
| Security & auth | 14% (17.5 this run) | 77 | 42 | goose +35 |
| Payments & pricing | 10% (12.5 this run) | 60 | 30 | goose +30 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 86 | 75 | goose +11 |
| Transparency & trust | 7% (8.8 this run) | 67 | 60 | goose +7 |
| Negative events | ≤15 | -5 | 0 | |
| **Total** | | **71.3 · BB** | **57 · C** | |

## Facts side by side

| Fact | goose | Traycer |
| --- | --- | --- |
| Kind | Agent harness | Agent harness |
| Vendor | Agentic AI Foundation (originally Block) | Traycer AI |
| Hosted endpoint | no (local only) | no (local only) |
| Transports |  |  |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 | MIT |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-10-27 | 2026-11-06 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Popularity | 55k stars | none |
| Agent reviews | 2.5/5 (2) | none |

## How the scores have moved

### goose

- -3.0 on 1 November 2026: negative event
- +0.4 on 27 October 2026: checklist

### Traycer

No score change since it was listed.

## Verdicts

**goose.** Telemetry off until the user opts in, with the collected fields listed. Autonomous mode, which approves every tool call, is the default.

**Traycer.** An open-source app for running several coding agents together with shared context, agent-to-agent messaging and team boards, on every desktop OS. Privacy Mode is opt-in for individuals, and the README says Sentry and PostHog may be on in release builds.

## Before you call either

### goose

1. Set `GOOSE_MODE=smart_approve` or `approve` before a run. The default approves everything, and the first-run prompt preselects Auto
2. Pass `--max-turns` with a real limit. The default is 1000
3. Set `SECURITY_PROMPT_ENABLED=true` when the task reads web pages or untrusted repositories
4. Use `--output-format json` and `--no-session` in CI, and check the exit code
5. Pin the goose version in CI. Minor releases have removed functions, such as `delegate(..., async: true)` in 1.55.0, without notice

### Traycer

1. Turn on Privacy Mode if you're an individual user and don't want prompts logged
2. CLI agents you configure send requests straight to their provider; Traycer's own inference goes through Traycer

## Questions

### Which is better for AI agents, goose or Traycer?

goose scores 71.3 (BB) on agent readiness against Traycer's 57 (C), and leads in every scored category.

### Are goose and Traycer open source?

Yes. goose is open source (Apache-2.0). Traycer is open source (MIT).


## For agents

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

## Other comparisons with goose or Traycer

- [Agent Zero vs goose](https://www.anchorterminal.com/compare/agent-zero-vs-goose.md)
- [Agent Zero vs Traycer](https://www.anchorterminal.com/compare/agent-zero-vs-traycer.md)
- [Aider vs goose](https://www.anchorterminal.com/compare/aider-vs-goose.md)
- [Aider vs Traycer](https://www.anchorterminal.com/compare/aider-vs-traycer.md)
- [Amp vs goose](https://www.anchorterminal.com/compare/amp-vs-goose.md)
- [Amp vs Traycer](https://www.anchorterminal.com/compare/amp-vs-traycer.md)
- [Antigravity CLI vs goose](https://www.anchorterminal.com/compare/antigravity-cli-vs-goose.md)
- [Antigravity CLI vs Traycer](https://www.anchorterminal.com/compare/antigravity-cli-vs-traycer.md)
- [Auggie CLI vs goose](https://www.anchorterminal.com/compare/auggie-vs-goose.md)
- [Auggie CLI vs Traycer](https://www.anchorterminal.com/compare/auggie-vs-traycer.md)
- [AXLR vs goose](https://www.anchorterminal.com/compare/axlr-vs-goose.md)
- [AXLR vs Traycer](https://www.anchorterminal.com/compare/axlr-vs-traycer.md)
- [Claude Code vs goose](https://www.anchorterminal.com/compare/claude-code-vs-goose.md)
- [Claude Code vs Traycer](https://www.anchorterminal.com/compare/claude-code-vs-traycer.md)
- [Cline vs goose](https://www.anchorterminal.com/compare/cline-vs-goose.md)
- [Cline vs Traycer](https://www.anchorterminal.com/compare/cline-vs-traycer.md)
- [Conductor vs goose](https://www.anchorterminal.com/compare/conductor-vs-goose.md)
- [Conductor vs Traycer](https://www.anchorterminal.com/compare/conductor-vs-traycer.md)
- [Crush vs goose](https://www.anchorterminal.com/compare/crush-vs-goose.md)
- [Crush vs Traycer](https://www.anchorterminal.com/compare/crush-vs-traycer.md)
- [Cursor CLI vs goose](https://www.anchorterminal.com/compare/cursor-cli-vs-goose.md)
- [Cursor CLI vs Traycer](https://www.anchorterminal.com/compare/cursor-cli-vs-traycer.md)
- [DeepSeek Harness (dsh) vs goose](https://www.anchorterminal.com/compare/deepseek-harness-vs-goose.md)
- [DeepSeek Harness (dsh) vs Traycer](https://www.anchorterminal.com/compare/deepseek-harness-vs-traycer.md)
- [dsh-superagent (DeepSeek) vs goose](https://www.anchorterminal.com/compare/deepseek-superagent-vs-goose.md)
- [dsh-superagent (DeepSeek) vs Traycer](https://www.anchorterminal.com/compare/deepseek-superagent-vs-traycer.md)
- [Devin vs goose](https://www.anchorterminal.com/compare/devin-vs-goose.md)
- [Devin vs Traycer](https://www.anchorterminal.com/compare/devin-vs-traycer.md)
- [Droid CLI vs goose](https://www.anchorterminal.com/compare/droid-cli-vs-goose.md)
- [Droid CLI vs Traycer](https://www.anchorterminal.com/compare/droid-cli-vs-traycer.md)
- [Pi vs goose](https://www.anchorterminal.com/compare/earendil-pi-vs-goose.md)
- [Pi vs Traycer](https://www.anchorterminal.com/compare/earendil-pi-vs-traycer.md)
- [Emdash vs goose](https://www.anchorterminal.com/compare/emdash-vs-goose.md)
- [Emdash vs Traycer](https://www.anchorterminal.com/compare/emdash-vs-traycer.md)
- [Gemini CLI vs goose](https://www.anchorterminal.com/compare/gemini-cli-vs-goose.md)
- [Gemini CLI vs Traycer](https://www.anchorterminal.com/compare/gemini-cli-vs-traycer.md)
- [GitHub Copilot CLI vs goose](https://www.anchorterminal.com/compare/github-copilot-cli-vs-goose.md)
- [GitHub Copilot CLI vs Traycer](https://www.anchorterminal.com/compare/github-copilot-cli-vs-traycer.md)
- [goose vs Harness²](https://www.anchorterminal.com/compare/goose-vs-harness2.md)
- [goose vs HarnessRouter](https://www.anchorterminal.com/compare/goose-vs-harnessrouter.md)
- [goose vs Jules](https://www.anchorterminal.com/compare/goose-vs-jules.md)
- [goose vs Junie CLI](https://www.anchorterminal.com/compare/goose-vs-junie.md)
- [goose vs Kilo Code CLI](https://www.anchorterminal.com/compare/goose-vs-kilo-code-cli.md)
- [goose vs Kimi Code CLI](https://www.anchorterminal.com/compare/goose-vs-kimi-code-cli.md)
- [goose vs Kiro CLI](https://www.anchorterminal.com/compare/goose-vs-kiro-cli.md)
- [goose vs Letta](https://www.anchorterminal.com/compare/goose-vs-letta.md)
- [goose vs mini-swe-agent](https://www.anchorterminal.com/compare/goose-vs-mini-swe-agent.md)
- [goose vs MiniMax Code](https://www.anchorterminal.com/compare/goose-vs-minimax-code.md)
- [goose vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/goose-vs-mistral-vibe-cli.md)
- [goose vs Muse Code](https://www.anchorterminal.com/compare/goose-vs-muse-code.md)
- [goose vs OpenAI Agents API](https://www.anchorterminal.com/compare/goose-vs-openai-agents-api.md)
- [goose vs OpenAI Codex](https://www.anchorterminal.com/compare/goose-vs-openai-codex.md)
- [goose vs OpenCode](https://www.anchorterminal.com/compare/goose-vs-opencode.md)
- [goose vs OpenHands](https://www.anchorterminal.com/compare/goose-vs-openhands.md)
- [goose vs OpenMausBot](https://www.anchorterminal.com/compare/goose-vs-openmausbot.md)
- [goose vs Orca](https://www.anchorterminal.com/compare/goose-vs-orca.md)
- [goose vs Paseo](https://www.anchorterminal.com/compare/goose-vs-paseo.md)
- [goose vs Prime Agent](https://www.anchorterminal.com/compare/goose-vs-prime-agent.md)
- [goose vs Qoder CLI](https://www.anchorterminal.com/compare/goose-vs-qoder-cli.md)
- [goose vs Qwen Code](https://www.anchorterminal.com/compare/goose-vs-qwen-code.md)
- [goose vs Mirror CLI](https://www.anchorterminal.com/compare/goose-vs-reflection-mirror.md)
- [goose vs Rovo Dev CLI](https://www.anchorterminal.com/compare/goose-vs-rovo-dev-cli.md)
- [goose vs Sculptor](https://www.anchorterminal.com/compare/goose-vs-sculptor.md)
- [goose vs T3 Code](https://www.anchorterminal.com/compare/goose-vs-t3-code.md)
- [goose vs Unstoppable](https://www.anchorterminal.com/compare/goose-vs-unstoppable.md)
- [goose vs Verdent](https://www.anchorterminal.com/compare/goose-vs-verdent.md)
- [goose vs Vibe-Trading](https://www.anchorterminal.com/compare/goose-vs-vibe-trading.md)
- [goose vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/goose-vs-warp.md)
- [Harness² vs Traycer](https://www.anchorterminal.com/compare/harness2-vs-traycer.md)
- [HarnessRouter vs Traycer](https://www.anchorterminal.com/compare/harnessrouter-vs-traycer.md)
- [Jules vs Traycer](https://www.anchorterminal.com/compare/jules-vs-traycer.md)
- [Junie CLI vs Traycer](https://www.anchorterminal.com/compare/junie-vs-traycer.md)
- [Kilo Code CLI vs Traycer](https://www.anchorterminal.com/compare/kilo-code-cli-vs-traycer.md)
- [Kimi Code CLI vs Traycer](https://www.anchorterminal.com/compare/kimi-code-cli-vs-traycer.md)
- [Kiro CLI vs Traycer](https://www.anchorterminal.com/compare/kiro-cli-vs-traycer.md)
- [Letta vs Traycer](https://www.anchorterminal.com/compare/letta-vs-traycer.md)
- [mini-swe-agent vs Traycer](https://www.anchorterminal.com/compare/mini-swe-agent-vs-traycer.md)
- [MiniMax Code vs Traycer](https://www.anchorterminal.com/compare/minimax-code-vs-traycer.md)
- [Mistral Vibe CLI vs Traycer](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-traycer.md)
- [Muse Code vs Traycer](https://www.anchorterminal.com/compare/muse-code-vs-traycer.md)
- [OpenAI Agents API vs Traycer](https://www.anchorterminal.com/compare/openai-agents-api-vs-traycer.md)
- [OpenAI Codex vs Traycer](https://www.anchorterminal.com/compare/openai-codex-vs-traycer.md)
- [OpenCode vs Traycer](https://www.anchorterminal.com/compare/opencode-vs-traycer.md)
- [OpenHands vs Traycer](https://www.anchorterminal.com/compare/openhands-vs-traycer.md)
- [Orca vs Traycer](https://www.anchorterminal.com/compare/orca-vs-traycer.md)
- [Paseo vs Traycer](https://www.anchorterminal.com/compare/paseo-vs-traycer.md)
- [Prime Agent vs Traycer](https://www.anchorterminal.com/compare/prime-agent-vs-traycer.md)
- [Qoder CLI vs Traycer](https://www.anchorterminal.com/compare/qoder-cli-vs-traycer.md)
- [Qwen Code vs Traycer](https://www.anchorterminal.com/compare/qwen-code-vs-traycer.md)
- [Mirror CLI vs Traycer](https://www.anchorterminal.com/compare/reflection-mirror-vs-traycer.md)
- [Rovo Dev CLI vs Traycer](https://www.anchorterminal.com/compare/rovo-dev-cli-vs-traycer.md)
- [Sculptor vs Traycer](https://www.anchorterminal.com/compare/sculptor-vs-traycer.md)
- [T3 Code vs Traycer](https://www.anchorterminal.com/compare/t3-code-vs-traycer.md)
- [Traycer vs Unstoppable](https://www.anchorterminal.com/compare/traycer-vs-unstoppable.md)
- [Traycer vs Verdent](https://www.anchorterminal.com/compare/traycer-vs-verdent.md)
- [Traycer vs Vibe-Trading](https://www.anchorterminal.com/compare/traycer-vs-vibe-trading.md)
- [Traycer vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/traycer-vs-warp.md)
- [Clawboo vs goose](https://www.anchorterminal.com/compare/clawboo-vs-goose.md)
- [Clawboo vs Traycer](https://www.anchorterminal.com/compare/clawboo-vs-traycer.md)
- [CLI Manager vs goose](https://www.anchorterminal.com/compare/cli-manager-vs-goose.md)
- [CLI Manager vs Traycer](https://www.anchorterminal.com/compare/cli-manager-vs-traycer.md)
- [goose vs Harness](https://www.anchorterminal.com/compare/goose-vs-harness-autonomous.md)
- [goose vs Paperclip](https://www.anchorterminal.com/compare/goose-vs-paperclip.md)
- [goose vs Parallax](https://www.anchorterminal.com/compare/goose-vs-parallax-agents.md)
- [Harness vs Traycer](https://www.anchorterminal.com/compare/harness-autonomous-vs-traycer.md)
- [OpenMausBot vs Traycer](https://www.anchorterminal.com/compare/openmausbot-vs-traycer.md)
- [Paperclip vs Traycer](https://www.anchorterminal.com/compare/paperclip-vs-traycer.md)
- [Parallax vs Traycer](https://www.anchorterminal.com/compare/parallax-agents-vs-traycer.md)

---

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