Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Agent Comms

NPM · AGENT-COMMS

Cross-harness communication mesh for LLM agents — rooms, DMs, presence, and visibility over TCP

Available components

+1 this week 79 Trust /100

Last scanned (15 hours ago)

Scores higher than 63% of npm servers

Category Communication

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security82
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known high-severity CVE affects zod 4.4.3, a direct dependency. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • 59 of 290 dependencies flagged as unhealthy (1 deprecated). View diagnostics → Partial
Provenance & Transparency97
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to ExaDev/agent-comms). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 5 days ago).Pass
  • Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability30
  • AI-judged instruction clarity (poor).Fail
  • Context-footprint check failed: tool/resource definitions use about 516 tokens (~516/item across 1 items; 1 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage70
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 10% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 1 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 1 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 16 Nov 26 +6
    • Known CVEs: unverified → fail ▼ security
    • Stability: 0.97 → pass security
    • Dependency health: unverified → 0.93 ▲ functional
    • Package version: 8.15.24 → 10.0.16 functional
  • 15 Nov 26 −5
    • Known CVEs: fail → unverified ▼ security
    • Dependency health: 0.93 → unverified ▼ functional
    • Package version: 9.0.15 → 10.0.15 functional
    • Package version: 8.15.24 → 10.0.14 functional
    • Package version: 9.0.15 → 10.0.13 functional
    • Package version: 9.0.15 → 10.0.12 functional
    • Package version: 9.0.15 → 10.0.10 functional
    • Package version: 9.0.15 → 10.0.9 functional
    • Package version: 9.0.15 → 10.0.8 functional
    • Package version: 9.0.15 → 10.0.7 functional
    • Package version: 9.0.15 → 10.0.1 functional
    • Package version: 9.0.15 → 10.0.0 functional
    • Package version: 9.0.15 → 9.1.2 functional
  • 14 Nov 26 +2
    • Malware scan: pass → unverified ▼ security
    • Known CVEs: fail → unverified ▼ security
    • Schema quality: 371 → 516 ▼ functional
    • Dependency health: 0.93 → unverified ▼ functional
    • Tool coverage: 0% → 10% ▲ functional
    • Package version: 8.15.25 → 9.0.15 functional
    • Package version: 8.15.25 → 9.0.14 functional
    • Package version: 8.15.25 → 9.0.13 functional
    • Package version: 8.15.25 → 9.0.12 functional
    • Package version: 8.15.25 → 9.0.11 functional
    • Package version: 8.15.25 → 9.0.6 functional
    • Package version: 8.15.25 → 9.0.5 functional
    • Package version: 8.15.25 → 9.0.1 functional
  • 13 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Nov 26 0
    • Package version: 8.15.24 → 8.15.25 functional
  • 11 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Nov 26 +2
    • Source repository: unverified → pass ▲ security
    • Stability: pass → 0.77 functional
  • 8 Nov 26 −5
    • Provenance: pass → unverified ▼ security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed npm/agent-comms@10.0.16

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo ExaDev/agent-comms
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/ExaDev/agent-comms/.github/workflows/ci.yml@refs/heads/main
Rekor log index 3915435042
Predicate type SLSA build provenance https://slsa.dev/provenance/v1
Subject digest sha512:14259608dc3146a4294a5b0e052e6d60f276726f1125bdc9394a59f68b0e851a4f31c3139b010cecc344dfbe735076ab77be12542697dcd2c4cd2ea6a

Background: How many MCP packages publish verified provenance →

Vulnerabilities 1 finding
ID CVE Severity Vector Fix available
GHSA-mrhx-c7xc-m3w5 CVE-2023-54404 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 290 packages
Packages resolved 290
Deprecated 1
Stale 57
No linked repository 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 1 exposed · ~516 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
agent_comms ~516

Cross-harness agent communication mesh. Actions: register, update, whoami, web_url, create_room, list_rooms, join_room, leave_room, send, dm, list_agents, read_room, invite, decline_invite, kick, destroy_room. Pending incoming messages are included in every response.

NameTypeReqDescription
actionstringyes–
adapterstring––
agentstring––
capabilitystring––
codestring–gateway_redeem_connection_code: the code's nonce. An unsigned connection code is a bearer hint, not authentication: redeeming it trusts whatever device-id its text names, whoever wrote it, so it is n…
connectionIdstring––
contentstring––
delegationsRemainingnumber––
descriptionstring––
devicestring––
expiresnumber––
expiresAtstring––
fingerprintstring–gateway_redeem_connection_code: a PGP fingerprint you already trust. Supplying it makes an unsigned code refused, and the signing key must match it.
grantstring––
hoststring––
idstring––
machineboolean––
meshVisibilitystring––
methodstring––
namestring––
passphrasestring––
policystring––
portnumber––
principalboolean––
privateKeystring––
publicKeystring–gateway_redeem_connection_code: armored PGP public key to verify the code's signature against. Supplying it makes an unsigned code refused.
reasonstring––
replyTostring––
requestIdstring––
requesterIdstring––
roomstring––
signaturestring–gateway_redeem_connection_code: the code's detached PGP signature, when it has one.
sincestring––
statusstring––
streamingBehaviorstring––
tagsarray––
targetstring––
timeoutMsnumber––
ttlMsnumber––
typestring––
visibilitystring––

No output schema declared.

No examples provided.

Install

How do I install the Agent Comms MCP server?

Agent Comms runs locally as an npm package, launched with npx -y agent-comms. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · agent-comms

# add to Claude Code
claude mcp add exadev-agent-comms -- npx -y agent-comms
Common questions

What is the Agent Comms MCP server?

Agent Comms is an MCP server listed in the public MCP registry as io.github.ExaDev/agent-comms. Cross-harness communication mesh for LLM agents, rooms, DMs, presence, and visibility over TCP. This page covers its npm package (agent-comms).

Is the Agent Comms MCP server safe to use?

Agent Comms scores 79 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 21 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Agent Comms MCP server expose?

Agent Comms exposes 1 tool: agent_comms. Their descriptions and schemas cost roughly 516 tokens of context every time the server is loaded.

Is the Agent Comms MCP server still maintained?

Agent Comms is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Agent Comms MCP server under?

Agent Comms declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the Agent Comms MCP server?

VerifyMCP ran 16 checks on Agent Comms, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.