Atlas / MCP servers / sttruji / mundane-mcp

mundane-mcpSAFE

mcp/sttruji/mundane-mcp

MCP server for Mundane: let your AI agent hire verified humans for real-world tasks — errands, photos, queues, in-person bookings. 35 tools, connect to the hosted endpoint over Streamable HTTP or self-run over stdio. Escrow-backed, ID-verified, policy-screened.

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
—
Transport
stdio · streamable-http
License
Apache-2.0
Stars
0
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

A thin adapter exposing the Mundane agent-to-human marketplace as thirty-five MCP tools (post_task, search_workers, make_offer, await_task_update, ...). Once connected, the server advertises each tool's full input schema to your agent over MCP, so there's no separate schema doc to keep in sync.

Two ways to connect. Point your client at Mundane's hosted endpoint (https://api.mundane.market/mcp) and install nothing, or run this adapter yourself over stdio — the same way you'd run a filesystem or database MCP server locally.

Hosted is the shorter path and stays current on its own. Running it yourself keeps the adapter on your machine and pinned to a version you control; in that mode one process is tied to exactly one agent's API key for its whole lifetime. Either way the tools, their schemas, and your spend limits are identical — it is the same code.

Tools

All thirty-five, grouped by when you reach for them. Each tool advertises its full input schema over MCP, so this table is orientation rather than a substitute for the schema your client already sees.

Finding and hiring

Chained jobs

Seve

Read from source at commit 768c48f27158OBSERVED · 2026-10-14
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code (pypi)
claude mcp add mundane-mcp --env MUNDANE_API_KEY=${MUNDANE_API_KEY} --env MUNDANE_API_KEY=${MUNDANE_API_KEY} -- None mundane-mcp==0.1.19
claude-code (oci)
claude mcp add mundane-mcp:0.1.19 --env MUNDANE_API_KEY=${MUNDANE_API_KEY} --env MUNDANE_API_KEY=${MUNDANE_API_KEY} -- docker run -i --rm ghcr.io/sttruji/mundane-mcp:0.1.19:None
03

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
declared (7 observation(s))
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (3)

LOWObfuscation / stealth · obf.decode_call · CWE-506, CWE-94
tests/test_proof_retrieval.py:42
with PILImage.open(BytesIO(base64.b64decode(block.data))) as image:
LOWObfuscation / stealth · obf.decode_call · CWE-506, CWE-94
tests/test_proof_retrieval.py:179
len(base64.b64decode(image.data)) <= server.MAX_PROOF_OUTPUT_BYTES
LOWInventory / provenance · mcp.no_tools_extracted · CWE-1104
server.json
Why it matters. the tool list is enumerated at runtime by tools/list, not declared in source
Fix. the page says so rather than showing an empty table

Gates applied: no_behavioural_pass.

Audited 2026-10-14 · audit v0.4.1 · source sha 768c48f27158full audit observations/trust-audit/mcp-server/sttruji__mundane-mcp.json · Report an issue / request a re-scan
04

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-14768c48f27158SAFEB89first audit
05

Questions

What is the mundane-mcp MCP server?

MCP server for Mundane: let your AI agent hire verified humans for real-world tasks — errands, photos, queues, in-person bookings. 35 tools, connect to the hosted endpoint over Streamable HTTP or self-run over stdio. Escrow-backed, ID-verified, policy-screened.

Is mundane-mcp safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does mundane-mcp need?

It reads MUNDANE_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does mundane-mcp run?

It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as mundane-mcp.

How current is this page?

The grade is for one exact copy of the source (768c48f27158), read on 2026-10-14. The repository is watched and re-audited when it changes.

Advertisement