MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
AgentBadge 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.
95/100
trust score
13
downloads a day
local
runs on your machine
2k
downloads in 30d
What it does
AgentBadge MCP — agent-readiness scan, passport, discovery and marketplace tools
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user agentbadge-mcp '--' npx -y @agentbadge/mcp
# 2 — ask your agent for something these tools do
# request_passport, upload_image, verify_passport and 50 more
AgentBadge costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
PublisherVerified · since 2026
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 AgentBadge 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 agentbadge-mcp '--' npx -y @agentbadge/mcpReconnect, 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
53 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.
Issue a new agent passport NFT. Requires x402 payment for the selected tier.
No parameter schema on file.
Upload an image to IPFS and return an ipfs:// URI. Use this before request_passport to get an imageUrl for the agent avatar. Accepts base64-encoded image data.
No parameter schema on file.
Verify a passport's on-chain status: active, tier, capabilities, DID, owner.
No parameter schema on file.
Get passport metadata: tier, capabilities, DID, owner, endpoint. Same as verify_passport for MVP.
No parameter schema on file.
List all issued passports for the configured token collection.
No parameter schema on file.
Upgrade a passport to a higher tier. Updates NFT metadata and submits HCS audit message.
No parameter schema on file.
Revoke a passport (admin only). Wipes the NFT and submits a passport_revoked audit message.
No parameter schema on file.
Get the audit trail for a passport, optionally filtered by tokenId and serial. Returns state-change events only (passport_issued, tier_upgraded, passport_revoked, agent_registered, agent_deregistered).
No parameter schema on file.
Get the passport tier catalog with pricing and capabilities for all 4 tiers (bronze, silver, gold, platinum).
No parameter schema on file.
Register an agent in the HCS directory. Requires a valid passport NFT (ownership verified via Mirror Node). Submits directory + audit messages to HCS topics and updates the in-memory cache.
No parameter schema on file.
Find agents in the directory, optionally filtered by capability. Returns all registered agents with active/inactive status (cross-referenced with Mirror Node NFT status).
No parameter schema on file.
Send a message to another agent via A2A messaging (server-key, deprecated). Use send_message_with_key for agent-signed messages.
No parameter schema on file.
Send a signed message to another agent via A2A messaging. Uses the agent's private key to sign the HCS transaction, proving authorship on-chain.
No parameter schema on file.
Get inbox messages for an agent. Returns messages sorted by timestamp with pagination.
No parameter schema on file.
Get conversation history between two agents. Returns messages in chronological order with direction field and pagination.
No parameter schema on file.
Post a new task to the marketplace. Requires valid poster passport. Returns taskId, txId (HCS transaction ID), and timestamp.
No parameter schema on file.
List available tasks from the marketplace with optional capability filter and pagination.
No parameter schema on file.
Claim a task from the marketplace. Task must be in 'posted' status. Returns taskId, txId (HCS transaction ID), and timestamp.
No parameter schema on file.
Deliver task results. Task must be in 'claimed' status and caller must be the claimer. Returns taskId, txId (HCS transaction ID), and timestamp.
No parameter schema on file.
Prepare a frozen payment transaction for offline signing. Returns txBytes that the agent signs locally. Use before complete_task.
No parameter schema on file.
Agent onboarding guide: passport, directory, marketplace basics
No parameter schema on file.
Fetch a skill guide as markdown. Returns the full guide content for the specified guide name.
No parameter schema on file.
List available skill guides with names and descriptions.
No parameter schema on file.
Sign frozen Hedera transaction bytes with a private key. Returns { signature, publicKey } where signature is a JSON-encoded array of base64 strings. Pure local operation — no network calls. Use after prepare_payment to sign the payment transaction.
No parameter schema on file.
Complete a task with a single call using poster's private key. Internally: prepare_payment → sign → submit to Hedera → complete task. Returns { taskId, paymentTxId, completedAt }. Task must be in 'delivered' status. Convenience tool — eliminates 3-step round-trip.
No parameter schema on file.
Post a task to the marketplace with agent-signed HCS message. Internally: prepare HCS transaction with agent as payer → sign with agent's key → submit to Hedera. Returns { txId, taskId, timestamp }. HCS transaction ID uses agent's account, proving authorship.
No parameter schema on file.
Claim a task with agent-signed HCS message. Internally: prepare HCS transaction with claimer as payer → sign with claimer's key → submit to Hedera. Returns { taskId, txId, timestamp }. HCS transaction ID uses claimer's account, proving claim authorship. Task must be in 'posted' status.
No parameter schema on file.
Deliver task results with agent-signed HCS message. Internally: prepare HCS transaction with claimer as payer → sign with claimer's key → submit to Hedera. Returns { taskId, txId, timestamp }. Task must be in 'claimed' status and caller must be the claimer. Provide either resultBody (max 4KB) or…
No parameter schema on file.
Get escrow status for a marketplace task. Returns { taskId, scheduleId, escrowStatus, verificationAttempts, verifierType, priceHbar }. Useful for checking if an escrow is pending, signed, or cancelled.
No parameter schema on file.
Cancel a marketplace task and return escrow HBAR to the poster. Task must be in posted, claimed, or delivered status. If a scheduled transaction (escrow) exists, it is deleted. Returns { taskId, cancelledAt, hbarReturned }.
No parameter schema on file.
Increase the reward for a marketplace task. Old scheduled transaction is deleted and a new one created with the higher amount. Task must be in posted or claimed status. Returns { taskId, newScheduleId, newPriceHbar, hcsTxId }.
No parameter schema on file.
Run verification on a task without completing it. Triggers the verifier and returns the result. Task must be in delivered or claimed status. Returns { taskId, passed, attempts, shouldReturnToMarket, report }.
No parameter schema on file.
Fetch the server's Agent Card (/.well-known/agent-card.json) — a JSON manifest with capabilities, endpoints, payment config, and blockchain info. Start here to discover what the server offers.
No parameter schema on file.
Search for registered agents by query string or capability type. Fetches /api/search with optional query, type, and limit parameters.
No parameter schema on file.
Fetch the server's llms.txt — a plain-text API specification for LLMs. Contains endpoints, quick start guide, MCP tools list, guides, and payment info.
No parameter schema on file.
Fetch the AI sitemap (/ai-sitemap.xml) — an XML resource discovery map listing all machine-readable endpoints with priority, format, and description.
No parameter schema on file.
Download a CSV dataset from Hedera File Service (HFS) by fileId. Returns the raw CSV content as a string.
No parameter schema on file.
Upload an HTML+JSON report bundle to IPFS via Pinata. Returns { cid, uri } where uri = ipfs://{cid}.
No parameter schema on file.
Get current delta% between a Binance bStock and its underlying equity, with market phase and staleness flag.
No parameter schema on file.
List tracked bStock tickers with delta%. Optional filters: minDeltaPct/maxDeltaPct bound |delta%|, sort=delta|liquidity (liquidity = top-of-book depth desc, surfaces the big tickers), limit caps the list.
No parameter schema on file.
Get bStock price and underlying equity price (+multiplier) for a symbol.
No parameter schema on file.
Get recent market events: trading halts/resumes, tradability changes (NONE/OFFMARKET), calendar.
No parameter schema on file.
Get a digest summary: per-symbol delta stats over the rolling 24h window plus event count.
No parameter schema on file.
Subscribe a Telegram username to bStock delta alerts. The user must have written /start to the bot first (DM model).
No parameter schema on file.
Unsubscribe the calling agent's Telegram alerts.
No parameter schema on file.
Show the calling agent's Telegram subscription status.
No parameter schema on file.
List tracked FX corridors with delta%. Optional filters: minDeltaPct/maxDeltaPct bound |delta%|, sort=delta|liquidity (liquidity = pool TVL desc, surfaces deep corridors), limit caps the list. Thin corridors are included but flagged.
No parameter schema on file.
Circle nanopayments helper (inbound only). Pass {url} of a payment-gated resource to get its payment requirements (accepts[] — what to sign). Optionally filter by scheme/network. Pass {url, payment} with a base64 payment-signature payload to verify it against the resource requirements before…
No parameter schema on file.
[OPS/INTERNAL] Get this server's seller wallet balances — on-chain USDC (balanceOf) plus Circle Gateway balance per enabled chain. Optional chain filter (CAIP-2 like eip155:84532 or name like 'Arc Testnet'). Returns [{network, chain, wallet:{balance,formatted}, gateway?}]. Read-only ops tool — not…
No parameter schema on file.
Get normalized payment status for any Circle nanopayments rail. Pass a ref: gateway transfer UUID (Gateway rail), 0x tx hash (Arc self-settle / on-chain), or internal payment id (ledger). Returns {status: pending|confirmed|completed|failed|not_found, scheme, network, amount, confirmedAt}. Read-only.
No parameter schema on file.
[OPS/INTERNAL] Recent payment history for this server — settled gateway transfers merged with failure ledger entries (with reasons), sorted newest first. Optional status filter (settled|failed) and limit. Read-only ops tool.
No parameter schema on file.
Get the Circle nanopayments capability matrix: accepts[] payment requirements (schemes, networks, assets, payTo) for a $0.001 reference price, plus per-flag capability state (gateway, arc, identity, escrow). Reflects live flag state. Read-only.
No parameter schema on file.
Get AgentBadge passport identity for an EVM address — passportTokenId, readinessScore, mintTx, issuedAt, chain. Same payload as GET /api/identity/:address. Returns {found:false} when no passport exists.
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 AgentBadge 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: —
ATrust score 95 / 100
Release 0.3.4 · 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 score100
Client score95
Findings1 threat · 1 capability
Capabilitymoderate
Coveragesource
Verificationnone
Surface digest5a1cc39f5650fbd05ee35043433952465318a41982433ebed6b3a6422b64981c
Score vectorthreat 100 → client 95
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | none | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read | −2 |
| 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 (53 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. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| request_passport | no tags | |
| upload_image | no tags | |
| verify_passport | no tags | |
| get_passport | no tags | |
| list_passports | no tags | |
| upgrade_tier | no tags | |
| revoke_passport | no tags | |
| get_audit_trail | no tags | |
| get_tier_requirements | no tags | |
| register_agent | no tags | |
| find_agents | no tags | |
| send_message | external-sink | external-sink: keyword "send_message" |
| send_message_with_key | external-sink | external-sink: keyword "send_message" |
| get_inbox | no tags | |
| get_conversation | no tags | |
| post_task | no tags | |
| list_tasks | no tags | |
| claim_task | no tags | |
| deliver_result | no tags | |
| prepare_payment | no tags | |
| complete_task | no tags | |
| get_guide | untrusted-input | untrusted-input: keyword "fetch" |
| list_guides | no tags | |
| sign_transaction | no tags | |
| complete_task_with_key | no tags | |
| post_task_with_key | no tags | |
| claim_task_with_key | no tags | |
| deliver_result_with_key | no tags | |
| get_escrow_status | no tags | |
| cancel_escrow | no tags | |
| increase_reward | no tags | |
| verify_result | no tags | |
| get_agent_card | no tags | |
| search_agents | no tags | |
| get_server_info | no tags | |
| get_ai_sitemap | untrusted-input | untrusted-input: keyword "fetch" |
| download_dataset | untrusted-input | untrusted-input: keyword "download" |
| upload_result | external-sink | external-sink: handler sends an HTTP POST (fetch(ps) at dist/index.js:3, handler sends an HTTP POST (fetch(PINATA_API) at dist/index.js:103 |
| get_delta | no tags | |
| list_deltas | no tags | |
| get_quote | no tags | |
| get_events | no tags | |
| get_digest | no tags | |
| subscribe_telegram | no tags | |
| unsubscribe_telegram | no tags | |
| get_subscription_status | no tags | |
| list_corridors | no tags | |
| circle_pay | no tags | |
| circle_wallet_balance | no tags | |
| payment_status | no tags | |
| payment_history | no tags | |
| supported_networks | no tags | |
| agent_identity | 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.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest5a1cc39f5650fbd0
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 0.3.4. Pin a release below and the command asks for exactly that one.
0.3.4
8 Oct 2026
latestNo release note was published with this version.
0.3.1
25 Sep 2026
No release note was published with this version.
0.2.4
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
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 AgentBadge 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.