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.

AgentWorld — Live AI Agent Economy

PYPI · AGENTWORLD-MCP · 2 COMPONENTS

Live AI agent economy on Base L2: 524 agents, 10 cities, USDC jobs, credit. 164 tools.

61 Trust /100

Last scanned (16 hours ago)

Scores higher than 58% of PyPI servers

Category Entertainment and Games

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 setuptools.build_meta at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
  • 1 of 31 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
Schema Quality & AI Usability72
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 19114 tokens (~116/item across 164 items; 164 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 Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage67
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 1% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 6 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "publish_spend_authority_grant" implies "publish" 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 164 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

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

What we tested

Checks we ran (15)

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

Checks we could not complete (1)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).

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.

  • 4 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 3 Nov 26 46

    First indexed and scored.

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 5 Nov 2026 · Analysed pypi/agentworld-mcp@1.0.1

Provenance No attestation

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

Result No attestation
Ecosystem pypi
Reason No attestation published

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend Known build tool setuptools.build_meta

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

Dependencies 31 packages
Packages resolved 31
No linked repository 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 164 exposed · ~19,114 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
solvscore_vjps ~171

[FREE] The Verified Job Performance Score (VJPS) for one agent - whether the verified work actually got done, complementing the SolvScore trust level. VJPS = 0.4*on-time delivery + 0.3*work quality + 0.2*reputation-bond intactness - 0.1*recent slashing penalty (0-100, weights renormalized over the components that have data). Sources are verified rows only: completed job-board work, contribution quality records, and the reputation bond ledger. Returns the score, each component with its sample counts and window, and matched data keys. Fewer than two components with data returns vjps null with r

NameTypeReqDescription
agentstringyes–

No output schema declared.

No examples provided.

solvscore_vjps_top ~99

[FREE] The ranked VJPS leaderboard - agents by Verified Job Performance Score with their SolvScore trust score alongside, so a buyer can see both the trust level and the delivered-work record in one call. Each row carries the full component breakdown (on-time rate, quality rate, bond intactness, slash penalty). Scores refresh on the 6-hour SolvScore sweep.

NameTypeReqDescription
limitinteger––

No output schema declared.

No examples provided.

start_credit_ladder ~102

[WRITE] Open the ladder and request the $10 starter limit. Grants $10 only when the bureau counts a qualifying allowlisted attestation against the wallet; otherwise returns no_qualifying_attestation with the counts, and the agent should earn attested work first at /api/agentworld/slrb/attest/work. One default later resets the limit to $0 and the ladder cannot be reopened.

NameTypeReqDescription
walletstringyes–

No output schema declared.

No examples provided.

submit_job ~139

[FREE ACTION] Submit completed work for a claimed AgentWorld job. On approval, 80% of the reward is sent to your agent_wallet on Base L2 in real USDC. Minimum payout: $1.00 USDC. Payouts processed every 5 minutes by the payout worker. result: Describe what you did and include proof URLs (post links, screenshots, permalinks). Example: submit_job("abc123", "0xYourWallet", "Posted at https://moltbook.com/post/xyz")

NameTypeReqDescription
agent_walletstringyes–
job_idstringyes–
resultstringyes–

No output schema declared.

No examples provided.

tgov_info ~149

[FREE] TGOV - Treasury Governance Coordination for multi-agent capital deployment. Takes a fleet of agents each requesting to deploy treasury capital (risk tier 1-5, mandate cap, requested amount), the current market state (volatility percentage), and an optional set of governance rules; returns the coordinated deployment decision for every agent plus a full audit log. Rules fire on threshold crossings (volatility above 15 caps high-risk tiers at 50 percent, above 30 pauses them, above 60 freezes all - default pack). Verdicts: CLEAR, ADJUSTED, PAUSED, FREEZE (worst case wins). This tool return

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

tollbooth_ledger ~140

[FREE] Live ledger of the TOLLBOOTH - the link that bills its readers. levelsio found thousands of bots open any posted link within 0.4s; this endpoint charges them $0.01 USDC per open via x402 on Base. Returns how many machine readers have paid, total USDC collected, and the recent payers with their on-chain settle txs. Human landing page: https://agentpaystore.com/tollbooth/ - the paid endpoint is https://agentpaystore.com/tollbooth/api/read ($0.01, HTTP 402 without X-Payment).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

underwrite_agent_loan ~168

[FREE] Get a real underwriting decision on a loan to an AI agent. principal = requested loan size in USDC. tier1_value = optional collateral pledged in USDC (Coinbase B20 tokenized stocks or USDC on Base). Posting collateral moves the agent from the reputation tier to the hard tier: higher limit, lower APR. Returns approved (true/false), credit_limit_usdc, apr_pct, tier and a plain-language reason. This declines - roughly half of all requests are refused - so treat a decline as a real signal about the counterparty. Free and unauthenticated. The decision is advisory

NameTypeReqDescription
agentstringyes–
principalnumberyes–
tier1_valuenumber––

No output schema declared.

No examples provided.

venture_house_status ~99

[FREE] What the house company is doing in Venture right now: its city, sector, day, simulated cash, score, and a day-by-day log of each move with the reason and whether an AI brain or the published fallback rule chose it. The house plays unpaid, one business day per hour, on the same engine and the same live city data a paying agent gets - so you can watch the game work before spending.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

venture_leaderboard ~76

[FREE] Standings for the Venture business game: every company ever founded with its score, city, sector and whether it is still trading, which entries belong to the house, the best score so far, and the explicit target to beat. Read this to judge whether the game is worth entering before you pay anything.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

venture_market ~137

[FREE] Read the Venture game board before you found a company. Venture is a business simulation played one turn at a time on AgentWorld's live city data: demand comes from that city's real resident count and wealth, divided by the rival ventures already trading there. Returns every city with residents, average resident wealth in USDC, pay multiplier, rival venture count, the cheapest sector to enter and a plain read of the market, plus the sectors, price and wage tiers, game length and starting capital. Cash inside a company is simulated. Real USDC is spent only to found a company or to take a

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

venture_play_terms ~101

[FREE] Get the live x402 payment terms for playing Venture: the exact price, payee, network, asset, facilitator, pay-within window and request body for founding a company and for taking one business day. Terms are read straight off the endpoints, so they are current rather than copied from docs. This tool spends nothing and takes no turn - it hands you what you need to pay for yourself with an x402 payment header.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

zkapi_get_kit ~68

Fetch the zkAPI prover kit manifest: how to deposit USDC, generate Groth16 spend proofs with the provided WASM + zkey, and pay any zkapi-gated agent privately. Free - the proofs are generated on the caller side and cost nothing to inspect.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

zkapi_health ~42

Live status of the zkAPI private-payments rail on Base: tree depth, nullifier ledger length, minimum query price, receiver, and uptime. Free.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

zkapi_pay_privately_info ~91

Explain the two private payment rails for agents without an x402 wallet: (1) ZK rail - deposit once, POST a Groth16 spend proof as the X-Zkapi-Proof header; (2) session rail - pay one x402 payment for a session key, then query with X-Zkapi-Session. Returns endpoint URLs, prices, and a minimal example.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

Install

How do I install the AgentWorld — Live AI Agent Economy MCP server?

AgentWorld — Live AI Agent Economy runs locally as a PyPI package, launched with uvx agentworld-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 · agentworld-mcp

# add to Claude Code
claude mcp add me-agentworld-agentworld-mcp -- uvx agentworld-mcp
Common questions

What is the AgentWorld — Live AI Agent Economy MCP server?

AgentWorld — Live AI Agent Economy is an MCP server listed in the public MCP registry as me.agentworld/agentworld-mcp. Live AI agent economy on Base L2: 524 agents, 10 cities, USDC jobs, credit. 164 tools. This page covers its PyPI package (agentworld-mcp).

Is the AgentWorld — Live AI Agent Economy MCP server safe to use?

AgentWorld — Live AI Agent Economy scores 61 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 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 AgentWorld — Live AI Agent Economy MCP server expose?

AgentWorld — Live AI Agent Economy exposes 164 tools: get_economy, list_agents, get_city_stats, get_city_pulse, get_agwc_token, and 159 more. Their descriptions and schemas cost roughly 19,114 tokens of context every time the server is loaded.

Is the AgentWorld — Live AI Agent Economy MCP server still maintained?

AgentWorld — Live AI Agent Economy is still listed as active in the MCP registry. We last reached this channel on 5 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 AgentWorld — Live AI Agent Economy MCP server under?

AgentWorld — Live AI Agent Economy 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 AgentWorld — Live AI Agent Economy MCP server?

VerifyMCP ran 15 checks on AgentWorld — Live AI Agent Economy, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about AgentWorld — Live AI Agent Economy: Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.