MCP connectors by com.textforagents

You cancelled the run — did the work actually stop?

Prove real MCP clients can connect: 5-client x 3-IdP OAuth matrix with shim fixes.

Parallel-burst abuse testing for agent APIs with replayable evidence packs.

Per-SDK verdict matrix for signed A2A Agent Cards: which signatures verify in each SDK.

Pair-level MCP+A2A conformance verdicts for the exact pair you delegate across.

Pays your endpoint like a stranger would and signs a checkout conformance verdict.

Fork-replay one recorded span from a failed agent run and get an attribution verdict.

Recovery loop for agent tool catalogs: measured confusion, ranked fixes, signed recovery receipts.

Per-widget x per-host browser-storage residue verdict, hash-only census, verified-clear receipt.

Concurrent two-client overlap probe proving MCP servers do not cross-deliver tool results.

Outcome-verified watchdog for scheduled agents. $0.002/check.

Annotation-survival conformance for MCP tools. Receipt $0.01, check $4.99, plans $9.99/$19.99.

Live-payload conformance probes with signed receipts: ABSENT/EMPTY/PARTIAL/COMPLETE/BROKEN.

Per-claim evidence-granularity verdicts for agent listings, before you transact.

Pre-run parity probe for scheduled agents: signed PARITY / NO-GO verdict naming the failing gate.

Rehearsal range: mirror a site, rehearse the workflow, earn a drift-bound promotion receipt.

History-seeded rewrite-regression verdicts, signed per class.

Checkpoint-paired twin trials for agent fleet changes with blinded verdicts.

Census and digest-verify a remote MCP server's loadable skills per host persona.

Real MCP handshake witness graded per-client, signed expiring receipt.