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.

Manager.io MCP

PYPI · MANAGER-MCP · SCANNED SEP 14

MCP server for Manager.io bookkeeping: read-first with opt-in scoped task and write tools

Available components

−16 this week 59 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 Security50
  • Malware scan not yet available for this package.Unverified
  • 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 23 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency32
Schema Quality & AI Usability57
  • AI-judged instruction clarity (fair).Partial
  • Tool/resource definitions use about 438 tokens (~43/item across 10 items; 10 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
  • Stability observed for 25 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 Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 10 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 Manager.io MCP server?

Manager.io MCP runs locally as a PyPI package, launched with uvx manager-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 · manager-mcp

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

  • 14 Sept 26 −15
    • Malware scan: pass → unverified security
  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 −3
    • Stability: pass → 0.77 functional
  • 11 Sept 26 0
    • Stability: 0.97 → pass security
  • 10 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.

  • 7 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.

  • 5 Sept 26 −2
    • Stability: pass → 0.80 functional
  • 4 Sept 26 0
    • Stability: 0.97 → pass 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 14 Sept 2026 · Analysed pypi/manager-mcp@0.2.6

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 23 packages
Packages resolved 23
Stale 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 10 exposed · ~438 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
aged_payables ~30

Aged payables snapshot (read-only).

NameTypeReqDescription
from_date
to_date

Structured output declared, but exposes no named fields.

No examples provided.

aged_receivables ~36

Aged receivables / outstanding customer balances (read-only snapshot).

NameTypeReqDescription
from_date
to_date

Structured output declared, but exposes no named fields.

No examples provided.

balance_sheet ~27

Balance sheet snapshot (read-only).

NameTypeReqDescription
from_date
to_date

Structured output declared, but exposes no named fields.

No examples provided.

bank_balances ~47

Bank/cash balances snapshot (read-only). For search/drill-in of individual accounts use list_records/get_record on bank_accounts.

NameTypeReqDescription
from_date
to_date

Structured output declared, but exposes no named fields.

No examples provided.

get_record ~67

Fetch one collection record by GUID via Manager form endpoint (e.g. /customer-form/{key}). chart_of_accounts has no single form. For bank/cash account detail use resource=bank_accounts (not bank_balances).

NameTypeReqDescription
keystringyes
resourcestringyes

Structured output declared, but exposes no named fields.

No examples provided.

list_records ~108

Search/page a curated collection. Core: customers, suppliers, sales_invoices, purchase_invoices, chart_of_accounts, bank_accounts. Also writable domains when present in discovery (e.g. receipts, payments, sales_quotes). bank_accounts is the searchable collection; use bank_balances for snapshot balances.

NameTypeReqDescription
page_sizeinteger
resourcestringyes
skipinteger
sort_by
sort_by_desc
term

Structured output declared, but exposes no named fields.

No examples provided.

list_resources ~40

List curated Manager.io capabilities. Default is read-only (10 tools). Task tools register when write scopes match; CRUD tools are deprecated unless raw scope is set.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

profit_and_loss ~29

Profit and loss snapshot (read-only).

NameTypeReqDescription
from_date
to_date

Structured output declared, but exposes no named fields.

No examples provided.

tax_summary ~27

Tax summary snapshot (read-only).

NameTypeReqDescription
from_date
to_date

Structured output declared, but exposes no named fields.

No examples provided.

trial_balance ~27

Trial balance snapshot (read-only).

NameTypeReqDescription
from_date
to_date

Structured output declared, but exposes no named fields.

No examples provided.

Common questions

What is the Manager.io MCP server?

Manager.io MCP is listed in the public MCP registry as io.github.flumpiey/manager-mcp. MCP server for Manager.io bookkeeping: read-first with opt-in scoped task and write tools. This page covers its PyPI package (manager-mcp).

Is the Manager.io MCP server safe to use?

Manager.io MCP scores 59 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 14 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 Manager.io MCP server expose?

Manager.io MCP exposes 10 tools: list_resources, list_records, get_record, aged_receivables, aged_payables, and 5 more. Their descriptions and schemas cost roughly 438 tokens of context every time the server is loaded.

Is the Manager.io MCP server still maintained?

Manager.io MCP is still listed as active in the MCP registry. We last reached this channel on 14 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.