Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add TonPC64/mcp-a2a-bridge --skill setupgit clone --depth 1 https://github.com/TonPC64/mcp-a2a-bridgeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tonpc64/mcp-a2a-bridge/setup)<a href="https://agentmods.dev/skills/tonpc64/mcp-a2a-bridge/setup"><img src="https://agentmods.dev/badge/skills/tonpc64/mcp-a2a-bridge/setup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tonpc64/mcp-a2a-bridge/setup"><img src="https://agentmods.dev/badge/skills/tonpc64/mcp-a2a-bridge/setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00011 | $0.00530 |
| Opus 5.5 | $0.00004 | $0.00212 |
| Sonnet 5.5 | $0.00002 | $0.00106 |
| Haiku 4.5 | $0.00001 | $0.00053 |
Grade A, and why
setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Setup Skill
Use this workflow when installing or starting this project. Choose MCP-only unless the optional dashboard is needed.
Prerequisites
- Python 3.11 or later
uv- Node.js 24.15+ and npm only for dashboard development or rebuilding dashboard assets
Procedure
- Clone the GitHub repository and enter it.
- Create the environment and choose one profile:
- MCP-only:
uv venv --python 3.11thenuv pip install -e .. - MCP + dashboard:
uv venv --python 3.11thenuv pip install -e ".[dashboard]".
- MCP-only:
- Configure agents in
.a2a-agents.jsonor setA2A_BRIDGE_CONFIGto an absolute registry path. Treat headers as secrets and never commit the registry. - Register
uv run --directory /absolute/path/to/mcp-a2a-bridge mcp-a2a-bridgewith the selected MCP host. - For the dashboard profile, run
npm --prefix dashboard ci,npm --prefix dashboard run build, thenuv run mcp-a2a-bridge-dashboard. - Enable activity reporting with
A2A_BRIDGE_DASHBOARD=1on each bridge process that should appear. - Use loopback by default. For trusted tokenless LAN access, explicitly set
A2A_BRIDGE_DASHBOARD_HOST; otherwise setA2A_BRIDGE_DASHBOARD_TOKENand put the service behind TLS and network controls.
Verification
uv lock --checksucceeds.uv run mcp-a2a-bridgestarts without dashboard dependencies in MCP-only mode.- Dashboard profile builds and serves
127.0.0.1:9100. - The dashboard token protects HTML, static assets, API, and SSE routes.
Pitfalls
- MCP-only does not need Node/npm.
- A tokenless non-loopback dashboard is only for trusted LANs; never expose it to the public internet.
- Build the frontend after source changes; the Python service serves
dashboard/dist. - Do not copy personal paths or real tokens from examples.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 49 lines · 11 tokens per session scan A 9f4fe09bb4c4
setup is a skill published in the GitHub repository TonPC64/mcp-a2a-bridge (0 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 530 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
remember
A memory-saving skill that stores facts, preferences, decisions, tasks, and other context in Super Memory, a local semantic memory store.
recall
A memory-search skill for finding previously saved information in Super Memory, a semantic memory store.
omni-mcp
Connect to the OmniRoute MCP server (110 tools, 3 transports: SSE/stdio/HTTP). Covers routing, cache, compression, memory, skills, providers, and audit tools across 33 permission scopes.
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
cli-resilience
Inspect and manage circuit-breaker states, connection cooldowns, quota limits, and backoff levels from the CLI. Reset stuck providers and configure resilience thresholds.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.