Remote MCP server that checks an agent's intended action before it happens and returns ALLOW, VERIFY, REQUIRE_VERIFICATION or DENY with a Trust Receipt.
What you can do
Verify a planned action before execution and get a decision plus a Trust Receipt v1.3
Cover payments, purchases, delegation, approvals, writes, releases and commits in that check
Look up the evidence-check payment, network, endpoint and assurance-pricing requirements needed before an autonomous payment
When to use it
Worth adding when an assistant takes consequential actions such as payments, approvals, releases or commits and you want a pre-execution gate that records a decision. Less useful for read-only or low-stakes workflows.
Requirements
A remote streamable HTTP endpoint at agents.muj428.com; no packages, environment variables or headers are declared. The manifest declares no authentication, so no account or key setup is described.
Before you install
The server only returns a decision and receipt; it does not itself move funds, and a FREE_PREFLIGHT result carries execution_authority=false, so it should not be treated as authorization to act. The second tool describes payment and assurance-pricing requirements, so paid verification may be involved. No authentication is declared, so consider what action details you send to a third-party endpoint.
Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.wmujahid428-web%2Fmuj428-trust-layer/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.
VERIFY BEFORE ACT across payments, purchases, delegation, approvals, writes, releases, commits, and other consequential actions. Returns ALLOW, VERIFY, REQUIRE_VERIFICATION, or DENY plus Trust Receipt v1.3; FREE_PREFLIGHT execution_authority=false and no funds are moved.
Parametersactionrequiredevidenceexternalmilestoneaction_refamount_usdtrajectorycounterpartyirreversibleaction_historyevidence_countrisk_threshold+4 more
get_evidence_signal_requirements
Evidence Signal Requirements
Returns MUJ428 evidence-check payment, network, endpoint, and assurance-pricing requirements before an autonomous payment.
Takes no parameters.
Version history
1
v1.6.4LatestSep 16, 2026
Score
75%
75% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listedRequired15 pts
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
License10 pts
Declare a license in the repository or the registry entry.
