# 448c Agent Exec Agent Exec MCP server

Source: https://glimind.com/server/mcp-registry%2Forg.448c.agent-exec%2Fagent-exec
Registry id: `mcp-registry/org.448c.agent-exec/agent-exec`
Status: live (checked 2026-10-27T04:10:26.485Z)

## Verdict

448c Agent Exec Agent Exec MCP server answered 99.88% of Glimind's liveness checks over 30 days, better than 28% of MCP servers, with 1053 ms median handshake and 2 outages in 90 days. Its agent-readiness grade is A (94/100) across 49 tools, costing an agent about 15,490 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 99.88% | 28% of MCP servers |
| Median handshake latency | 1053 ms | 17% of MCP servers |
| p95 handshake latency | 3571 ms | — |
| Checks in 30 days | 5,027 | — |
| Outages, 90 days | 2 | — |
| Median recovery | 18 min | — |
| Agent-readiness score | 94/100 (A) | 78% of MCP servers |
| Tools | 49 | — |
| Tool-list size for an agent | ~15,490 tokens | 13% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "448c-agent-exec-agent-exec-mcp-server": {
      "type": "http",
      "url": "https://agent-exec.448c.org/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http 448c-agent-exec-agent-exec-mcp-server https://agent-exec.448c.org/mcp
```

## Tools (49)

- `attest_create`: PAID: we fetch a URL from OUR vantage point and return a signed, timestamped attestation of what we saw -- hash, byte count, HTTP status and headers, never the 
- `attest_read`: FREE and unauthenticated: read a previously-created attestation back by id, with its signature. This is how what you bought with attest_create comes back over M
- `check_address`: PAID: check an EVM address against public risk feeds (OFAC, community darklists, on-chain age) and get back a verdict, score and reasons in the same response th
- `check_url`: PAID: check a URL against public risk feeds (phishing lists, domain age, lexical signals) and get back a verdict, score and reasons in the same response the pay
- `claim_acquire`: PAID: atomically win a caller-named key for your own fleet -- an accountless compare-and-set. outcome "acquired" means you won it; outcome "held" is NOT an erro
- `claim_acquire_free`: FREE: win a caller-named key for 300 seconds, or learn who already holds it. Unlimited distinct keys per wallet, renewable by calling again. A sibling of claim_
- `claim_read`: FREE: who currently holds this key, if anyone -- scoped to YOUR wallet, so a stranger cannot probe your namespace. Checking your own lock must not cost again, o
- `claim_release`: FREE: give up a key you hold before it expires, so the next racer does not have to wait out your hold. Release signs its own domain-separated message, distinct 
- `claim_renew`: PAID: extend a hold you already have without losing your place in line -- the heartbeat that lets a lease be SHORT (so a crash frees it fast) while a live holde
- `create_inbox`: PAID: get a throwaway email address on a domain we own, live for 24 hours, to receive the verification mail a signup demands. RECEIVE ONLY -- nothing is ever se
- `deadman_confirm`: FREE: the live caller closes the loop before the lease expires, so the probe never runs. Deliberately NOT wallet-scoped -- possession of the id is the entire au
- `deadman_read`: FREE and unauthenticated: read an entry back by id, including its verdict and the raw probe response once resolved. This is how what you bought with deadman_reg
- `deadman_register`: PAID: register an intent you are about to act on irreversibly, with a lease and a verification probe (a GET plus a predicate). Confirm before the lease expires 
- `dns_lookup`: FREE: what we serve for a name under 448c.net -- its records, its owner and when it expires. No signature and no account: the zone is public, so reading it is t
- `dns_release`: FREE: release a name you own before it expires. It stops resolving at once. There is no refund and no undo, and the label is free for anyone else to rent. Owner
- `dns_renew`: PAID: push a name you own further out by another year. What it resolves to is untouched; only its expiry moves, and a repeated payment extends it rather than re
- `dns_rent`: PAID: rent <label>.448c.net for a year and point it where you say -- A, AAAA, CNAME and TXT records, so you can hold a TLS certificate by DNS-01 and pass domain
- `dns_rent_free`: FREE: one 24-hour name per wallet, so you can try the zone before paying -- the same label rules and records as dns_rent. Rent a year with dns_rent when it work
- `dns_set_records`: FREE: replace the whole record set of a name you own -- never merged. The rental window is untouched: repointing a name you already paid for costs nothing. Owne
- `drift_baseline`: FREE: the baseline snapshot we hold for one venue -- what a paid check would diff against, and when it was taken. Reading what you are about to buy a comparison
- `drift_check`: PAID: we re-fetch a venue we have snapshotted before, from OUR vantage point, and return what changed since the baseline -- the schema/rubric fields that moved,
- `drift_venues`: FREE: every venue id drift_check can be aimed at, with what we hold for each. A closed value set, not a pattern: without it a caller can honour the input schema
- `execute`: PAID: run code in an isolated, network-less sandbox and get stdout, stderr and exit code back. Call it once without payment to receive the price as an x402 Paym
- `free_inbox`: FREE: one live inbox per wallet for one hour, identity by your signature alone, so you can receive one code before paying for the 24 h tier. A sibling of create
- `handoff_deposit`: PAID: deposit a typed briefing for the process that takes over from you -- what is DONE (every entry carrying evidence of how it was verified), what is NOT done
- `handoff_read`: FREE and unauthenticated: read a briefing back by id. This is how what you bought with handoff_deposit reaches your successor over MCP. Deliberately needs no si
- `inbox_status`: FREE: the address, when it expires and how much mail is waiting in an inbox you own. Signed under its own domain, separate from the one read_inbox uses. Ownersh
- `listing_promote`: PAID: buy paid placement for a listing you own in this directory -- it ranks above free rows and reads tier "paid" for the life of the plan. Pay from the WALLET
- `pay_receipt`: FREE and unauthenticated: read a pay_send receipt back by id -- what the seller answered, when, and what the chain says became of your authorization. Deliberate
- `pay_requirements`: FREE: ask a seller, unpaid, what it charges, and get back the accepts[] of its own 402 -- the exact PaymentRequirements you have to sign before pay_send can del
- `pay_send`: PAID: deliver an x402 authorization YOU signed to a seller exactly once, then read the chain for what actually became of it, and get back an immutable receipt o
- `placement_cancel`: FREE and owner-signed: stop the weekly rechecks and drop the order. There is no refund for the remaining window, and entries already in a catalogue are the venu
- `placement_order`: PAID: we submit your service to every permissionless agent venue we hold a submitter for -- 17 of the 33 on-behalf venues today -- and prove, per venue, that th
- `placement_ready`: FREE and honest: does your own service publish a document a venue can read (/.well-known/x402, an agent card)? If it publishes none, no amount of submission wor
- `placement_status`: FREE and owner-signed: every venue of your order with its state (queued, submitted, listed, human-only, unfunded, failed), the evidence a landing was verified b
- `placement_venues`: FREE: the lane table -- every agent venue we have evaluated, which of the 3 lanes a submission takes (on-behalf, owner-proof, human-only), the VENUE's own fee, 
- `read_inbox`: FREE: the mail your inbox received, newest first, with any verification code and link already picked out -- from, to, subject, receivedAt, the plain text, codes
- `release_inbox`: FREE: give up an inbox you own before it expires. Its messages go with it and the local part is never issued again; later mail to it is dropped, never bounced. 
- `search_listings`: Free, unauthenticated search over agent-exec's directory of paid agent-facing services (same data as GET https://agent-exec.448c.org/listings). Returns a page o
- `service_card`: What agent-exec sells, what it costs, and exactly where to pay for it. This tool call itself is free and moves no money. Code execution can be bought right here
- `storage_buy`: PAID: store opaque bytes for the life of the plan you buy, owned by the wallet that pays, readable with no account. Returns the object id and when it expires; r
- `storage_delete`: FREE: delete an object you own before it expires, and free its bytes. There is no refund and no undo. Ownership is proved by the paying wallet, with no account:
- `storage_list`: FREE: list the objects your wallet owns -- id, label, size, when each was created and when it expires -- one page at a time. Ownership is proved by the paying w
- `storage_read`: FREE: read back an object you own, as base64. This is how what you bought with storage_buy comes back to you over MCP. Ownership is proved by the paying wallet,
- `storage_renew`: PAID: push an object you own further out, by buying it another plan term. The object is untouched; only its expiry moves. Returns the new and previous expiry. C
- `storage_replace`: PAID: overwrite the contents of an object you own, keeping its id, and buy it a fresh plan term at the same time. Omit label to keep the current one, pass an em
- `storage_usage`: FREE: how many objects your wallet is storing and how many bytes they occupy. Ownership is proved by the paying wallet, with no account: send any placeholder si
- `watch_read`: FREE: the current state of a watch you registered -- active, matched or expired, with the observation that matched. The id is the capability, so a successor pro
- `watch_register`: PAID: we poll a URL from OUR vantage point on your interval until your predicate matches or the ttl runs out, and keep the verdict for you to collect -- a wait 

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.