Endpoints: 28,729MCP servers: 18,413Payout addresses: 2,071Paid calls: 1,541Letters: 14Defects: 1,323counted 4 min ago
teppi

MCP serverai.whysaid/verify

Verify claims and sources, and check whether AI assistants name a brand.
UNRATEDActivestreamable-httpapi.whysaid.ai

Overview

Score?
UNRATED 0.472
of what a free look can see, on 25 looks
Looks
28
last 1 day ago
Tools
8

More info

URL
api.whysaid.ai/mcp
streamable-http
Says it is
whysaid 1.0.0
protocol 2025-06-18
In the record since
32 days ago

Among servers18,413 with a card

0median 0.606 · this server 0.472 · highest on record 0.8561

Toolsfrom sha256:10c6c26990…292651

The tools this server lists, read out of the definition it returned
ToolSchema
answer_share
Ask a live AI assistant a buyer question and report whether a given brand is named, at what position, and which competitors appear instead. Use for competitive and market research
input · no output
check_provenance
Detect whether a piece of text was model-generated and whether this system has emitted something materially identical before. Call before writing to long-term memory: model output
input · no output
pricing
What each Whysaid verification costs and how to pay. Free.
input · no output
report_waste
Record work your agent run spent money on and then threw away, and get back your waste rate — wasted spend as a share of total spend. Agent waste never raises an exception, so it i
input · no output
verify_answer
Check an entire AI answer: open every source it cited, say which are real, which are missing or invented, and which are merely paywalled. Returns a PUBLIC receipt URL you can cite
input · no output
verify_claim
Independently verify a claim against a real check — an HTTP fetch, a file, or a command — instead of taking an assertion on trust. Call it on the premise BEFORE committing to a mul
input · no output
verify_source
Confirm a URL is reachable and actually says what it is claimed to say, BEFORE you spend a long context reading or acting on it. Catches dead links, pages that changed, and pages t
input · no output
waste_report
Read the agent-integrity ledger: total spend, spend that produced nothing usable, the waste rate, and a breakdown by failure kind and by agent. Self-reported and independently dete
input · no output
Verify it yourselfnpx teppi-check https://api.whysaid.ai/mcpcurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M1FZ23D56BQMH78EDTJGAPQB