mcp-registry/work.agentexchange/store · v1.0.0
Also listed as mcp-registry/io.github.rccola990-cloud/x402-agent-store, mcp-registry/work.agentexchange.store/mcp · primary listing: mcp-registry/io.github.rccola990-cloud/x402-agent-store
claude mcp add --transport http glimind https://glimind.com/mcp?ref=install-server. Other clientsAs of 2026-11-22 14:14 UTC, the Agent Exchange store MCP server is up with a Glimind reliability score of 90/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks.
Pay-per-call data for agents over x402: crypto prices, on-chain reads, web research, public tenders.
Point your MCP client at this streamable-http endpoint: https://store.agentexchange.work/mcp
144 tools on one server. Tool-selection accuracy drops as the menu grows, and some clients (e.g. Cursor) cap the number of active tools.
Group tools by task into smaller servers or toolsets, and merge near-duplicates behind one tool with a mode parameter. How to fix →
116 parameter(s) across 59 tool(s) have no description.
Add a "description" to each parameter with its format and an example ("ISO 8601 date, e.g. 2026-10-17"). This is the commonest cause of wrong arguments on the first call. How to fix →
8 tool(s) look like they change state (create/send/delete/pay…) but declare no destructiveHint.
Set annotations {"readOnlyHint": false, "destructiveHint": true|false, "idempotentHint": …}. Clients use these to ask the user before a side effect and to auto-approve safe reads. How to fix →
Loading this server's tool list costs an agent ~24,083 tokens before any work — more than 95% of MCP servers.
Split rarely-used tools into a separate server or a toolset the client can enable, or expose one "search tools" entry point. Many agents load every connected server's tools into every request. How to fix →
In the last 30 days: 3 tool(s) removed and 0 schema change(s).
Add new tools or optional parameters instead of renaming or removing; deprecate first (say so in the description) and remove later. Agents cache tool contracts. How to fix →
No tool declares an outputSchema.
Declare outputSchema and return structuredContent (MCP 2025-06-18+). Agents can then parse results without guessing, and chain tools reliably. How to fix →
140 of 144 tool(s) carry no readOnlyHint/destructiveHint annotations.
Annotate read-only tools with {"readOnlyHint": true}. Agents and gateways can then run them without a confirmation prompt, and route around destructive ones. How to fix →
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. 59 tool(s) still need parameter descriptions written by someone who knows the API. All of them as JSON: /v1/readiness/mcp-registry%2Fwork.agentexchange%2Fstore/fixes
{
"name": "brand_ai_visibility_check",
"description": "PREMIUM ($0.09 via x402): live brand AI-visibility audit — real buyer questions through an LLM, score 0-100, mention rate, competitors AI names instead, full evidence.",
"inputSchema": {
"type": "object",
"required": [
"brand",
"category"
],
"properties": {
"brand": {
"type": "string",
"description": "Brand or business name"
},
"market": {
"type": "string",
"description": "us|uk|de|jp|kr|fr|es|br|in, default us"
},
"category": {
"type": "string",
"description": "Buyer search category, e.g. 'CRM software'"
},
"x_payment": {
"type": "string",
"description": "Optional signed x402 payment payload (X-PAYMENT header value)"
}
}
},
"annotations": {
"readOnlyHint": true
}
}{
"name": "chain_batch_reads",
"description": "$0.005 via x402: up to TEN on-chain reads for ONE payment, run in parallel — native balance, nonce, contract-code check, ERC-20 balance, block number and gas price in any combination. Reconciling a wallet normally costs one payment per read; this is the same data for a fraction of the calls and the latency. Per-read failures are reported individually with a partial flag, so a batch never claims success it did not have.",
"inputSchema": {
"type": "object",
"properties": {
"chain": {
"type": "string",
"description": "base|ethereum|optimism|arbitrum|polygon|gnosis (default base)"
},
"reads": {
"type": "string",
"description": "Comma-separated ops, max 10: balance:0xADDR | nonce:0xADDR | code:0xADDR | erc20:0xTOKEN:0xWALLET | blocknumber | gas"
},
"x_payment": {
"type": "string"
}
}
},
"annotations": {
"readOnlyHint": true
}
}{
"name": "chain_ens_resolve",
"description": "$0.005 via x402: resolve ENS in either direction on Ethereum — pass an ENS name (vitalik.eth) to get its 0x address, or pass a 0x address to get its primary ENS name (and avatar when set). The identity read every wallet, payment and UX agent makes to verify who it's sending to, or to display a human-readable name instead of a raw hex address. Live ENS registry; one paid call instead of running your own resolver.",
"inputSchema": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "ENS name to resolve to an address, e.g. vitalik.eth"
},
"address": {
"type": "string",
"description": "0x address to reverse-resolve to its primary ENS name"
},
"x_payment": {
"type": "string"
}
}
},
"annotations": {
"readOnlyHint": true
}
}Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:
curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/work.agentexchange/store"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/work.agentexchange/store"}) over MCP.
earth_snapshot ~318 tokensearth_snapshot_json ~302 tokensmodels_models ~277 tokensthink_vote ~273 tokenswhale_transfer_alerts ~272 tokensStatic checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).
Operator? Fix these, then re-check live.
Shows whether the server is live and its agent-readiness score; it updates within the hour.
[](https://glimind.com/server/mcp-registry%2Fwork.agentexchange%2Fstore?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fwork.agentexchange%2Fstore?ref=badge"><img src="https://glimind.com/badge/mcp-registry%2Fwork.agentexchange%2Fstore.svg" alt="MCP server status"></a>
Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:d4b989ebad66b330…, first seen 2026-11-21, included at leaf 379810 of 383,964. Version history · verify what your client received.
Compare: most reliable devops servers · most reliable knowledge servers · most reliable search servers · most reliable data servers · most reliable ml servers
Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.
Claude Code
claude mcp add --transport http glimind https://glimind.com/mcp?ref=install-server
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"glimind": {
"type": "http",
"url": "https://glimind.com/mcp?ref=install-server"
}
}
}
A free Glimind key lets your agent check whether a server works right now before it calls it, and switch to a live one when it doesn't. No signup, no card.
As of 2026-11-22 14:14 UTC, the Agent Exchange store MCP server is up with a Glimind reliability score of 90/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks.
Agent Exchange store MCP server advertises 144 tools, including agent_enterprise_integration, agent_passport, agentforce_proxy, ai_category_ranking, ai_visibility_index.
Point your MCP client at this streamable-http endpoint: https://store.agentexchange.work/mcp
Glimind scanned all 144 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.
Status page: 90-day uptime, every outage and how long it lasted.
Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.
Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.