Agents MCP Server
MCP server for agent-to-agent communication over NATS with live session push via Claude Code Channels.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
Piotr1215
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
When Vitest UI server is listening, arbitrary file can be read and executed
AGENTS_HISTORY_MAX_AGE_MS30d JetStream stream retentionAGENTS_HISTORY_MAX_BYTES512 MiB JetStream stream capAGENTS_HISTORY_MAX_MSGS_PER_SUBJECT10000 Per-subject capAGENTS_HTTP_PORT3000 (code default) HTTP mode onlyAGENTS_LOG_FILE_unset_ When set, writes a local audit log (stdio installs); unset in the default Docker imageAGENTS_NATS_URLA NATS server reachable via , with JetStream enabledAGENTS_PUSH_TIMEOUT_MSAGENTS_SWEEP_INTERVAL_MSAGENTS_TRANSPORTThe server picks its transport at boot via :AGENTS_UNBOUND_TIMEOUT_MSSND_FROMAll four hints declared on every tool
13/13 tools missing one or more hints — agent_register (missing: destructiveHint, idempotentHint, openWorldHint); agent_deregister (missing: readOnlyHint, idempotentHint, openWorldHint); agent_broadcast (missing: destructiveHint, idempotentHint, openWorldHint), +10 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Descriptions match behaviour
1 tool describes read intent but its handler mutates — channel_send (line 77: appendFileSync(LOG_FILE, `[${ts}] [${type}] ${content}\n`))
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool inputs are validated
11/13 tool handlers declare input schemas (85%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
Only 3/13 tool handlers wrap calls in try/catch (23%)
Wrap each tool handler body in try/catch and return a structured error response.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Tool test coverage
Only 2/13 tools referenced in tests (15%)
Write tests that reference each tool by name so every tool has at least one test.
Dev dependencies
1 critical/high in dev-only deps (does not ship to users)
Upgrade dev dependencies when convenient.
Tool description accuracy
channel_send: description implies read-only but handler writes/deletes/executes
Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/piotr1215/agents-mcp-server)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check