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.

Fleetpost

PYPI · FLEETPOST-MCP · SCANNED SEP 21

A mailbox for your machines: read fleet capabilities, send a request. Offline, no server.

Available components

0 this week 77 Trust /100
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 Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 1 of 29 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency32
Schema Quality & AI Usability77
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 557 tokens (~92/item across 6 items; 6 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management90
  • Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "fleet_send_request" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Install

How do I install the Fleetpost MCP server?

Fleetpost runs locally as a PyPI package, launched with uvx fleetpost-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · fleetpost-mcp

# add to Claude Code
claude mcp add stanimirtenev-fleetpost-mcp -- uvx fleetpost-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "stanimirtenev-fleetpost-mcp": {
      "command": "uvx",
      "args": [
        "fleetpost-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "stanimirtenev-fleetpost-mcp": {
      "command": "uvx",
      "args": [
        "fleetpost-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add stanimirtenev-fleetpost-mcp -- uvx fleetpost-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "stanimirtenev-fleetpost-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "fleetpost-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add stanimirtenev-fleetpost-mcp --command uvx --arg fleetpost-mcp
# ~/.hermes/config.yaml
mcp_servers:
  stanimirtenev-fleetpost-mcp:
    command: "uvx"
    args: ["fleetpost-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "stanimirtenev-fleetpost-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "fleetpost-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add stanimirtenev-fleetpost-mcp -t stdio -c uvx -a fleetpost-mcp
// mcp.json
{
  "mcpServers": {
    "stanimirtenev-fleetpost-mcp": {
      "command": "uvx",
      "args": [
        "fleetpost-mcp"
      ]
    }
  }
}
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.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 −2
    • Stability: pass → 0.80 functional
  • 17 Sept 26 0
    • Stability: 0.97 → pass security
  • 16 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Sept 26 −2
    • Stability: pass → unverified security
    • Tool safety: pass → unverified security
    • Schema quality: 83 → 92 functional
    • Capabilities: pass → unverified functional
    • Tool coverage: 100 → unverified functional
    • First check of Schema quality: unverified functional
    • Stability: pass → 0.80 functional
    • Package version: 0.1.0 → 0.2.0 functional
  • 10 Sept 26 0
    • Stability: 0.97 → pass security
  • 9 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

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 Sept 2026 · Analysed pypi/fleetpost-mcp@0.2.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 29 packages
Packages resolved 29
No linked repository 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 6 exposed · ~557 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
fleet_capabilities ~51

What the machines in this fleet can do. Omit `machine` for all of them. Use this before asking another machine for something, to check it can actually do it.

NameTypeReqDescription
machine

Structured output declared, but exposes no named fields.

No examples provided.

fleet_handle ~67

Mark a request in this machine's own inbox as done, moving it to inbox/handled/. Do this only after the work is done and the answer has been sent. A request left at the top level counts as still pending and will keep being flagged.

NameTypeReqDescription
namestringyes

Structured output declared, but exposes no named fields.

No examples provided.

fleet_read_request ~37

Read one unhandled request from this machine's own inbox, by filename as reported by fleet_status.

NameTypeReqDescription
namestringyes

Structured output declared, but exposes no named fields.

No examples provided.

fleet_send_request ~245

Ask another machine in the fleet to do something, by dropping a request in its inbox. The machine may be offline; it will pick the request up on its next cycle. Every field below is required by the protocol, because a request missing them cannot be acted on. Ask for an *action*, not for access: if the task needs a credential this machine lacks, the machine that holds it does the work and returns the result. Secrets never travel. Args: to: Target machine name, as listed by fleet_status. topic: Short subject; also becomes part of the filename. what_is_wanted: Exactly what should be done. done_means: How the other side will know it finished — the acceptance test. valid_until: When this stops being worth doing (e.g. "2026-08-20"). reply_to: Where to put the answer. Defaults to this machine's inbox.

NameTypeReqDescription
done_meansstringyes
reply_to
tostringyes
topicstringyes
valid_untilstringyes
what_is_wantedstringyes

Structured output declared, but exposes no named fields.

No examples provided.

fleet_status ~107

What is waiting for this machine: unhandled requests in its inbox, whether the shared protocol changed, which other machines' capabilities are known, and when the last coordination cycle ran. Also what this machine is waiting on: requests it sent that the recipient has not picked up yet (`outstanding_sends`), each with when that recipient last ran a cycle — null there means it never has, so it will not see the request at all. Reads local files only.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

fleet_sync ~50

Run one coordination cycle now: pull this machine's inbox and the fleet's capabilities, then publish this machine's own descriptors if they changed. Never executes a request and never changes another machine's data.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

Common questions

What is the Fleetpost MCP server?

Fleetpost is an MCP server listed in the public MCP registry as io.github.StanimirTenev/fleetpost-mcp. A mailbox for your machines: read fleet capabilities, send a request. Offline, no server. This page covers its PyPI package (fleetpost-mcp).

Is the Fleetpost MCP server safe to use?

Fleetpost scores 77 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. 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 Fleetpost MCP server expose?

Fleetpost exposes 6 tools: fleet_status, fleet_capabilities, fleet_read_request, fleet_send_request, fleet_handle, fleet_sync. Their descriptions and schemas cost roughly 557 tokens of context every time the server is loaded.

Is the Fleetpost MCP server still maintained?

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