Access control for AI agents and MCP servers: allow, hold for approval, or block each tool call
HODLXXI Read-Only is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Public read-only MCP server for HODLXXI agent identity, trust, receipts, and verification.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http hodlxxi-read-only-mcp https://hodlxxi.com/agent/mcp
# 2 — ask your agent for something these tools do
# hodlxxi_get_agent_identity, hodlxxi_get_operator_continuity, hodlxxi_get_api_catalog and 23 more
HODLXXI Read-Only costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http hodlxxi-read-only-mcp https://hodlxxi.com/agent/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
26 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Return the canonical public agent identity document, including capabilities, pricing, endpoints, skills, messaging metadata, and trust-model declarations.
No parameter schema on file.
Return the public operator-continuity statement, operator and agent public keys, covenant status, rotation policy, and verification references.
No parameter schema on file.
Return the public RFC-style API linkset catalog with service descriptions, documentation links, and status links.
No parameter schema on file.
Return the Agent Skills discovery index with skill names, descriptions, URLs, types, and SHA-256 digests.
No parameter schema on file.
Return the live MCP discovery server card for https://hodlxxi.com/agent/mcp, which nginx routes to the separate read-only sidecar rather than the Flask monolith.
No parameter schema on file.
Return public NIP-17/NIP-59 messaging policy metadata, including intake status, custody limitations, accepted kind, and size ceiling.
No parameter schema on file.
Return OpenID Connect discovery metadata: issuer, authorization and token endpoints, JWKS URI, grants, scopes, PKCE, and signing algorithms.
No parameter schema on file.
Return OAuth authorization-server metadata, including the HODLXXI agent_auth discovery block and disabled registration endpoint references.
No parameter schema on file.
Return OAuth protected-resource metadata, including resource issuer, authorization servers, JWKS URI, scopes, and bearer method.
No parameter schema on file.
Return the public RSA JSON Web Key Set used to verify HODLXXI-issued JWT signatures. No private JWK fields are exposed.
No parameter schema on file.
Return the signed Agent Protocol discovery document with public endpoint links, trust surfaces, timestamp, and agent signature.
No parameter schema on file.
Return the signed capabilities document with job schemas, pricing, limits, endpoint registry, public skills, and messaging metadata.
No parameter schema on file.
Return the JSON Schema published for the signed HODLXXI capabilities document.
No parameter schema on file.
Return the checked-in public skill catalog with metadata, repository paths, and installation URLs.
No parameter schema on file.
Return the normalized marketplace listing with discovery links, job types, pricing, skills, reputation snapshot, chain health, and trust model.
No parameter schema on file.
Return aggregate public operating history, evidenced job counts, attestation count, trust and confidence averages, pattern distribution, and rolling trust trend.
No parameter schema on file.
Return paginated signed receipt attestations. limit must be 1-100 and offset must be non-negative.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | — |
| offset | integer | no | — |
Return the paginated public trust-event chain with hashes, receipt linkage, timestamps, public key, and signatures.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | — |
| offset | integer | no | — |
Return the signed Nostr announcement template, advertised NIP-89/NIP-90 kinds, discovery links, and explicit non-goals.
No parameter schema on file.
Return attestation-chain continuity status, event count, latest event hashes, and latest timestamp when available.
No parameter schema on file.
Return the machine-readable covenant countdown with chain height, spend paths, estimated unlocks, funding status, and conservative trust interpretation.
No parameter schema on file.
Return the compact trust summary for a validated public agent identifier.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | string | no | — |
Return a declared covenant artifact by validated covenant identifier, including descriptor, policy, funding status, public keys, and non-claims.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| covenant_id | string | no | — |
Return a public machine-readable trust or readiness report by validated report identifier, including its canonical SHA-256 field when present.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| report_id | string | yes | — |
Verify a previously issued receipt by job identifier and return verification status, validity, attestation, signed receipt, event hash, and QR pointer non-claims. This does not poll /agent/jobs and cannot mint a receipt.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | string | yes | — |
Return a previously issued signed receipt by job identifier. Optional requester-proof fields depend on the historical receipt.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | string | yes | — |
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install HODLXXI Read-Only or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither: the repository linked on this page is where this record was collected from, not a copy of what the address serves, so it is not graded in its place. So there is no grade — not a withheld one, an unmeasured one.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 0.1.1.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish HODLXXI Read-Only can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.