# Aider vs AXLR

> AXLR scores 70.6 (BB) to Aider's 47.1 (D) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/aider-vs-axlr
- Markdown: https://www.anchorterminal.com/compare/aider-vs-axlr.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: 2026-11-01

AXLR scores 70.6 (BB) on agent readiness against Aider's 47.1 (D), and leads in 5 of 7 scored categories. Aider leads on transparency & trust. Both do agent harnesses.

- Aider: grade D, 47.1/100, rank #1025 of 1253. Markdown https://www.anchorterminal.com/tools/aider.md · JSON https://www.anchorterminal.com/api/v1/tools/aider.json
- AXLR: grade BB, 70.6/100, rank #168 of 1253. Markdown https://www.anchorterminal.com/tools/axlr.md · JSON https://www.anchorterminal.com/api/v1/tools/axlr.json
- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md
- All 1000 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md

## Which one, for what

### Aider (D)

Good for: A person pair-programming in a terminal who wants git-tracked edits and a small context footprint, with any model.

Ahead on:
- Transparency & trust, 65 against 55

Also in its favour:
- No key needed to call it

Watch for: No release since 0.86.2 on 12 February 2026 and no commit since 22 May 2026

### AXLR (BB)

Good for: A program or bot that needs one governed execution at a time, with a policy, a budget, a sandbox profile and correlation ids it sets itself and a result object it reads back, on a machine it controls, with the model on OpenRouter, a local server or a native Anthropic or OpenAI key.

Ahead on:
- Reliability, 70 against 54
- Schema & documentation, 80 against 56
- Agent ergonomics, 83 against 65
- Maintenance & community, 79 against 13

Also in its favour:
- Agent-ready, a grade of BB or better
- No incidents deducted, where Aider loses 8 points for them

Watch for: The setup assistant turns autonomy on and leaves the exec sandbox off, so after setup the model's commands run with the person's rights, bar the destructive list


## Why the edge

### Maintenance & community: AXLR +66

- Aider (13): 0.86.2 on 2026-02-12, 231 days before this check (0). No release in the last 90 days (0). No commit on main since 2026-05-22, about 1,300 open issues and 512 open pull requests, and the CVE report (#5254) had no maintainer reply we could see (3). The PyPI package lags main, which declares Python 3.13 and 3.14 support that the release doesn't allow (5). CI passed on the last commits and dependencies are pinned, as of May (5).
- AXLR (79): v0.15.0 on 2026-10-25, with commits on main to 2026-11-01 (30). 21 releases between 4 and 25 October 2026 (20). One maintainer (368 of 399 commits, the rest by two agent accounts), 10 open issues that are his own trackers with no comments, about 100 merged pull requests and no outside report to measure a reply against (15). Not in the MCP registry; the Go module and a proto to generate clients from are the only client code, beside the GHCR image and Helm chart (5). Go 1.26 toolchain pinned, release actions pinned by commit SHA, a go-licenses check that the third-party bundle matches the dependency graph, and CI passing on main (9). 30+20+15+5+9 = 79.

### Schema & documentation: AXLR +24

- Aider (56): No machine-readable contract. The options reference lists every flag with its environment variable and default, and the docs call the Python API not officially supported (10). No llms.txt or Markdown versions of pages found in the site source (0). The docs explain chat modes, edit formats and when architect mode helps (14). Typed config through `.aider.conf.yml` and flags with defaults (10). Many usage examples and troubleshooting pages (12). A release history per version without dates (10).
- AXLR (80): An OpenAPI 3.1 file for the service (15 paths, 23 schemas, `mutualTLS` security scheme, `additionalProperties: false` on request bodies), a checked proto for the gRPC service, and the 19 MCP tools built from the same shared schemas (25). No llms.txt on either site (404), and the docs site renders HTML; the Markdown sources are in the repository (5). The product contract tables what each of the four interfaces can and cannot do, the work-mode table states each mode's purpose and tool policy, the transport parity ledger names every verb's arguments and behaviour, and `axlr_tools` tells the model to look for a tool before forging one (15). Typed inputs throughout, `Idempotency-Key` 16 to 128 safe ASCII characters, `expected_revision` a positive integer, policy levels, sandbox profiles and egress values enumerated, budgets as four integers, and the service rejects unknown fields, invalid types and bodies over 4 MiB (14). Examples in every guide, an error shape of `code`, `message` and `request_id`, named codes (`409 idempotency_conflict`, `400 invalid_cursor`, `422 invalid_policy`, `invalid_budget`, `sandbox_unavailable`, `not_ready`, `invalid_id`), a gRPC status mapping, and the worker's five statuses and three exit codes; no single error reference page (14). `/v1` routes and an OpenAPI version of 0.1.0 against a 0.15.0 release, and no changelog beyond the dated notes inside the docs (7). 25+5+15+14+14+7 = 80.

### Agent ergonomics: AXLR +18

- Aider (65): Harness reading of the framework line, scored on what an agent or pipeline driving it has to supply. Aider doesn't use tool calls or MCP. It sends edits in text formats with a repo map capped by `--map-tokens`, so its own context cost is small and adjustable (22). `--map-tokens`, `--max-chat-history-tokens` and single-shot `--message` runs (14). Plain-text output, with no JSON mode or documented exit codes (8). Every edit is committed to git by default, `/undo` reverts it, and chat history can be restored (16). Python only, with an unofficial Python API and no MCP for adding tools (5).
- AXLR (83): Harness reading of the framework line, scored on what a program driving it has to supply. Six local tools plus the host's bookkeeping tools; work modes and an execution policy hide the tools a run may not use, `axlr_catalog` searches the catalog instead of loading it, forged tools keep the request prefix for the prompt cache, and a context cap of 75,000 prompt tokens opens a successor session (20). `local_read`, `local_search` and `local_list` page with `offset`, `next_offset` and `max_bytes`; `StreamEvents` takes `after`, `max_events` (1 to 256) and `wait_ms`; a budget per execution in seconds, requests, tool calls and dollars; 32 tool calls a turn and `max_session_usd` (20). The `--exec` run ends in one `result` line with a status, the pending call, every call's outcome and the usage, and exits 0, 3 or 1; service errors carry codes an agent can act on; a budget stop says which limit (`budget: requests 20 reached`) and leaves the session resumable (16). `Idempotency-Key` on every turn, approval and direct call with cross-transport replay, `expected_revision` on decisions, `expected_sha256` on worker writes, and an interrupted effectful call left `uncertain` for an operator rather than retried (19). One command runs a task, but the first launch needs an OpenRouter key or a local server, the service needs a CA, a principals file and remote KMP and MADE before a first session, and the only SDK is the Go library (8). 20+20+16+19+8 = 83.

### Reliability: AXLR +16

- Aider (54): Read as a local package. aider-chat on PyPI, but the latest release (0.86.2) requires Python below 3.13, while main has moved on (18). The Ubuntu test workflow passed on every main run we loaded, the last on the 22 May 2026 merge, and a Windows workflow sits beside it (25). About 1,300 to 1,400 open issues and 512 open pull requests, with recent ones unlabelled and no maintainer reply we could see, among them uncaught exceptions (#5473, #5466) (5). HISTORY.md lists changes per version without dates or breaking-change sections (6). 0.86, pre-1.0, and classed 4 - Beta on PyPI (0).
- AXLR (70): Read as a local package, as claude-code, goose, opencode and openhands were. Release archives for Linux, macOS and Windows on amd64 and arm64 with a `.sha256` beside each, a GHCR image, an OCI Helm chart and source builds with Go 1.26, all stated in the docs; no Homebrew, npm or apt route (20). CI on main runs vet, race tests and a coverage gate above 80 per cent for both modules, with the sandbox tests required under bubblewrap, and the last ten runs on main to 1 November 2026 all passed; the release workflow tests on six native runners (25). 10 open issues, all opened by the founder on 19 and 21 October 2026 as trackers for service work (work modes, plugins, the sandbox setting, cost limits), none from an outside user and none a crash report, 0 open pull requests and about 100 merged; with 0 stars there is nobody else to report, so the handling of outside reports is untested (20). Tags are semver 0.x and the docs date each behaviour change inline ("until 14 October 2026…"), but the 21 releases have empty notes, there is no CHANGELOG.md, and the product contract records one retirement (the seven 1.0 skill definitions on 5 October 2026) without a notice period (5). Pre-1.0, which the README calls an evolving project (0). 20+25+20+5+0 = 70.

### Transparency & trust: Aider +10

- Aider (65): Apache-2.0 (30). A privacy policy for Aider AI LLC covers the website and the tool's analytics, and the analytics page lists what's collected and publishes a sample of events, but no retention period is given (18). No deprecation policy or dated notices found (3). Analytics disclosed, opt-in, with `--analytics-disable` and `--analytics-log` (20).
- AXLR (55): Apache-2.0 with a NOTICE (30). No privacy policy or terms on underpassai.com or axlr.underpassai.com; the docs' 'Where data goes' and 'Diagnostics and privacy' sections say that model requests go to OpenRouter, the local server or the native API, that Jev sends text to TypeSafe only when on, that sessions live under `$XDG_STATE_HOME/axlr`, that payload capture is off by default and redacted when on, and that traces are deleted after 30 days; nothing covers the engine downloads' or the catalog registry's handling of a client's requests (15). No deprecation policy; pre-1.0 changes are dated inline in the docs and the product contract records the 5 October 2026 retirement of the first skill catalogue after the fact (6). No telemetry to disclose, and the docs say in two places what leaves the machine and how to stop payload capture, though no single page says there is no telemetry (17). 30+15+6+17 = 68.

## Score by category

| Category | Weight | Aider | AXLR | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 54 | 70 | AXLR +16 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 56 | 80 | AXLR +24 |
| Agent ergonomics | 13% (16.2 this run) | 65 | 83 | AXLR +18 |
| Security & auth | 14% (17.5 this run) | 59 | 62 | AXLR +3 |
| Payments & pricing | 10% (12.5 this run) | 60 | 60 | even |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 13 | 79 | AXLR +66 |
| Transparency & trust | 7% (8.8 this run) | 65 | 55 | Aider +10 |
| Negative events | ≤15 | -8 | 0 | |
| **Total** | | **47.1 · D** | **70.6 · BB** | |

## Facts side by side

| Fact | Aider | AXLR |
| --- | --- | --- |
| Kind | Agent harness | Agent harness |
| Vendor | Aider AI LLC | Underpass AI |
| Hosted endpoint | no (local only) | no (local only) |
| Transports |  |  |
| Auth | None | OAuth or key |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 | Apache-2.0, with a NOTICE naming Tirso García Ibáñez as the copyright holder |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-02-12 | 2026-10-25 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no date given | no document linked |
| Popularity | 49k stars | 0 stars |
| Agent reviews | 1/5 (2) | none |

## How the scores have moved

### Aider

- -0.2 on 28 October 2026: new evidence
- +0.4 on 27 October 2026: checklist
- -0.2 on 8 October 2026: checklist

### AXLR

No score change since it was listed.

## Verdicts

**Aider.** Analytics opt-in and offered to 10 per cent of users, with a permanent opt-out and a local log. No release since 0.86.2 on 12 February 2026 and no commit since 22 May 2026.

**AXLR.** A pre-1.0 Go harness with an unusually complete service contract, mutual TLS with principal roles, required idempotency keys, a policy, budget and sandbox per execution, and a result object a program can read. The console's defaults after setup are autonomy on and no sandbox, the project has one maintainer and no outside users yet, and releases carry no notes.

## Before you call either

### Aider

1. Read `.aider.conf.yml` in any cloned repository before starting aider. Its `test-cmd` and `lint-cmd` run without asking
2. Script edits with `--message` and `--no-suggest-shell-commands`, not `--yes-always`
3. Use Python 3.12 or earlier for the PyPI release
4. Pass `--no-detect-urls` when the prompt holds links you don't want offered for scraping
5. Check `git log` after a run. Each edit is its own commit

### AXLR

1. Before the first prompt, set `approvals.autonomous` to false or run with `--approve none`, and turn `exec_sandbox.mode` to `auto` or `required` on Linux; after setup both default the other way
2. Drive a run with `axlr-tui --exec --json --policy <file> --budget <file> --sandbox <file>` and read only the last `result` line; exit 3 means a call waits for `--decide approve|deny` with `--session <id>`
3. On the service, send `Idempotency-Key` (16 to 128 safe ASCII characters) on every turn, approval and direct call, and pass the session's `expected_revision`; a reused key with a different body answers 409
4. A local model must return native tool calls (llama.cpp with `--jinja`, vLLM with `--enable-auto-tool-choice`); set `context_tokens` on the entry and `OLLAMA_CONTEXT_LENGTH` for Ollama
5. Leave `TYPESAFE_API_KEY` unset unless you want the setup assistant to switch Jev on, which sends requests and final answers to TypeSafe

## Questions

### Which is better for AI agents, Aider or AXLR?

AXLR scores 70.6 (BB) on agent readiness against Aider's 47.1 (D), and leads in 5 of 7 scored categories. Aider leads on transparency & trust.

### Are Aider and AXLR open source?

Yes. Aider is open source (Apache-2.0). AXLR is open source (Apache-2.0, with a NOTICE naming Tirso García Ibáñez as the copyright holder).


## For agents

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

## Other comparisons with Aider or AXLR

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

---

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