MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
Agent Mesh is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
85/100
trust score
5
downloads a day
local
runs on your machine
544
downloads in 30d
What it does
Auditable multi-agent coordination: fleets, P2P messaging, witnessed receipts, quorum.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user agent-mesh-mcp '--' npx -y meshfleet
# 2 — ask your agent for something these tools do
# spawn_fleet, fleet_status, list_fleets and 37 more
Agent Mesh costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
JOAll 1 server
johnmwhitman1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Agent Mesh as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user agent-mesh-mcp '--' npx -y meshfleetReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
40 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Spawn parallel agents. Returns fleet_id. An agent banks complete only when result_contract is ok; refused, blocked, artifact_missing, invalid, or absent banks failed.
No parameter schema on file.
Check fleet and agent status.
No parameter schema on file.
List all fleets with summaries (agent count, status, completion).
No parameter schema on file.
Set a per-fleet timeout override (in milliseconds). Agents exceeding this are auto-failed.
No parameter schema on file.
Get fleet outputs and loss tally. Only result_contract ok can bank complete; refused, blocked, artifact_missing, invalid, or absent banks failed. Declared outcome, not quality. Check lost first.
No parameter schema on file.
Send a P2P message from one agent to another within the same fleet. Set to_agent_id to "*" to broadcast to every other agent in the fleet (each recipient acks independently; see get_receipts).
No parameter schema on file.
Send a batch of P2P messages in ONE ledger transaction — use instead of repeated send_message calls for bulk fan-out (much faster: the recipient inbox is updated once per batch, not once per message). Atomic: one invalid message rejects the whole batch. Max 1000 messages per call.
No parameter schema on file.
Get messages in an agent's inbox, optionally since a timestamp.
No parameter schema on file.
Acknowledge a message, removing it from the agent's inbox. Writes an 'ack' receipt (per-recipient — a broadcast is acked independently by each recipient).
No parameter schema on file.
Write a non-consuming receipt on a message — the audit primitive. Use actions like 'seen', 'r-ack' (approve), 'retracted'. Unlike ack_message, the message stays in the inbox. One receipt per (message, agent, action); repeat calls are idempotent.
No parameter schema on file.
Get the full receipt trail for a message: who acked, who annotated, when. Answers 'who saw this and who acted on it'.
No parameter schema on file.
Audit the ledger's internal consistency: every receipt points at a real message and honors the idempotency key, acknowledged flags are supported by ack receipts, inboxes hold no consumed or dangling messages, and ratification tallies (quorum, signoffs, vote polarity, terminal status) recompute…
No parameter schema on file.
Versioned verifier output read from a dedicated read-only file snapshot; the handler performs no ledger writes. Normal parent-server startup recovery or migration may initialize or change the configured ledger before tool dispatch. Returns the unchanged internal-consistency report inside…
No parameter schema on file.
Opt-in verifier output read from a dedicated read-only file snapshot; the handler performs no ledger writes. Returns a detached meshfleet.verify/v3 report with one local consistency band per finding, derived only from its severity. Those labels are not provenance or confidence and do not establish…
No parameter schema on file.
Open a quorum vote ('council') over the fleet. Broadcasts a proposal; peers vote with cast_vote. Ratifies when approvals reach the quorum and every required signoff approves. Returns the proposal message_id.
No parameter schema on file.
Cast a vote on an open ratification. approve=true records approval, approve=false rejection. Re-casting CHANGES your effective vote (each change appends a new sequenced receipt — history is never rewritten); repeating your current vote is a no-op.
No parameter schema on file.
Read the live vote tally and current status (open / ratified / rejected / expired) of a ratification, and persist the status if it has reached a terminal state.
No parameter schema on file.
Evaluate every open ratification now and persist any that reached a terminal state (deadline expiry, silent-approval, unreachable quorum). The server also sweeps automatically every AGENT_MESH_RATIFY_SWEEP_MS (default 60s).
No parameter schema on file.
Register an agent's capabilities (role, skills, model) for routing.
No parameter schema on file.
Route a work description to the best-matching registered agents by keyword + role/skill overlap scoring (with synonym expansion), weighted by routing feedback (success/fail history). top_n controls how many matches to return (default 1, max = fleet size).
No parameter schema on file.
Offline projection of caller-supplied route-candidate snapshots. Does not persist, rank, execute, authorize, wake, or contact providers.
No parameter schema on file.
Advisory-only ranking over caller-supplied sanitized task traits and candidate snapshots. Does not persist, execute, authorize, wake agents, or contact providers.
No parameter schema on file.
Pure, caller-approved speculative backlog projection. Does not persist, execute, authorize, wake agents, contact providers, poll, allocate capacity, schedule, spend, send, or publish.
No parameter schema on file.
Record whether a routed task succeeded or failed. Future route_work calls for the same agent weight their score by accumulated outcomes (Wilson-style). NOTE: outcomes are currently accumulated PER AGENT, not per capability — capability_key is recorded for forward compatibility but does not yet…
No parameter schema on file.
List all available premade agents from .opencode/agents/ directories.
No parameter schema on file.
Attach an agent to a running fleet. It banks complete only when result_contract is ok; refused, blocked, artifact_missing, invalid, or absent banks failed.
No parameter schema on file.
Minimal liveness check. Returns { status: 'ok', timestamp }.
No parameter schema on file.
Subscribe to an agent's inbox via Server-Sent Events (SSE). Returns a stream URL that the agent opens to receive real-time push of incoming P2P messages. Falls back to polling get_inbox if SSE is unreachable. If the operator set MESHFLEET_AUTH_TOKEN, requests to the stream must carry it…
No parameter schema on file.
Subscribe to the unified fleet-wide event stream via Server-Sent Events (SSE). Returns a stream URL that emits every ledger event (messages, receipts, ratifications, spawns, completions, discussions) as it is appended. Keep-alive :hb comment frames are sent every 30s. Optional fleet_id filter…
No parameter schema on file.
Fleet health + liveness. Pass verbosity="summary" for a smaller routine probe (entrypoints map omitted); default "full" is the full BuildIdentityReport. Use get_build_identity for diagnostics.
No parameter schema on file.
Full BuildIdentityReport for the running install: package name/version, source_commit, entrypoint_count, per-entrypoint SHA-256 map, entrypoints_match_runtime bit. Diagnostic access to the install's identity.
No parameter schema on file.
Save a named fleet template (set of agent specs) for reuse. Names: lowercase letters, numbers, dashes, underscores.
No parameter schema on file.
List all saved fleet templates, sorted by name.
No parameter schema on file.
Return a fleet spec from a saved template, ready to pass to spawn_fleet.
No parameter schema on file.
Open a bounded, two-agent Discussion: sends the root question and (optionally) explicitly reserves one peer attempt, then waits until the conversation deadline for a settled answer. Message arrival never starts an agent by itself — wake_peer:true is the explicit, budgeted authority to run the peer…
No parameter schema on file.
The sole general-purpose Discussion run trigger. Atomically reserves one bounded attempt for a resident participant who is the current recipient of the canonical head, then launches it. Never waits for the reply. Duplicate concurrent calls return the existing active attempt or turn_already_active…
No parameter schema on file.
Submit the one reply an active wake attempt is authorized to produce. Never launches an agent. Rejects a second reply for the same attempt, a stale head, or a reply past the conversation/attempt deadline. close:true makes the conversation terminal; exhausting the last turn without close returns…
No parameter schema on file.
Read-only: derive and return a Discussion's full state — transcript, attempts, budget, and fail-closed status (invalid > closed > deadman > expired > exhausted > active > open) — from durable messages and receipts. Remains useful after every inbox entry has been acknowledged.
No parameter schema on file.
Record a first-class external work receipt (Hermes Kanban result contract).
No parameter schema on file.
Read back a work receipt by composite key. Returns the exact stored bytes plus
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Agent Mesh or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
BTrust score 85 / 100
Release 0.22.0 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score91
Client score85
Findings5 threat · 2 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digest8331dd5b908232166d5ea4036e2c4dec82073bcd934600405980f56eef8f8e81
Score vectorthreat 91 → client 85
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (40 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| spawn_fleet | code-execexternal-sink | code-exec: keyword "spawn" in tool name; external-sink: declares readOnlyHint: false, openWorldHint: true |
| fleet_status | no tags | |
| list_fleets | no tags | |
| set_fleet_timeout | state-write | state-write: declares readOnlyHint: false |
| collect_results | no tags | |
| send_message | external-sinkstate-write | external-sink: keyword "send_message"; state-write: declares readOnlyHint: false |
| send_messages | external-sinkstate-write | external-sink: keyword "send_message"; state-write: declares readOnlyHint: false |
| get_inbox | no tags | |
| ack_message | state-write | state-write: declares readOnlyHint: false |
| receipt | state-write | state-write: declares readOnlyHint: false |
| get_receipts | no tags | |
| verify_ledger | no tags | |
| verify_ledger_v2 | no tags | |
| verify_ledger_v3 | no tags | |
| open_ratification | state-write | state-write: declares readOnlyHint: false |
| cast_vote | state-write | state-write: declares readOnlyHint: false |
| tally_ratification | no tags | |
| sweep_ratifications | state-write | state-write: declares readOnlyHint: false |
| register_capability | state-write | state-write: declares readOnlyHint: false |
| route_work | no tags | |
| compile_route_candidates | no tags | |
| recommend_route | no tags | |
| plan_speculative_backlog | no tags | |
| record_routing_outcome | state-write | state-write: declares readOnlyHint: false |
| list_agents | no tags | |
| attach_agent | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| ping | no tags | |
| subscribe_inbox | no tags | |
| subscribe_events | no tags | |
| get_health | no tags | |
| get_build_identity | no tags | |
| save_fleet_template | state-write | state-write: declares readOnlyHint: false |
| list_fleet_templates | no tags | |
| spawn_from_template | code-exec | code-exec: keyword "spawn" in tool name |
| ask_peer | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| wake_agent | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| reply_discussion | state-write | state-write: declares readOnlyHint: false |
| get_discussion | no tags | |
| record_work_receipt | state-write | state-write: declares readOnlyHint: false |
| get_work_receipt | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest8331dd5b90823216
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.22.0. Pin a release below and the command asks for exactly that one.
0.22.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Agent Mesh can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.