
Servidor MCP de EchoRelay
Quais servidores MCP são de EchoRelay, do registro oficial e encontrados perguntando ao próprio domínio, se respondem e o que oferecem. Um programa verificou cada item; nada foi copiado da página do produto.
lido em 2026-10-26
- Nome no registrodev.echorelay/managementverificado no registro MCP
O nome no registro fica sob echorelay.dev. O registro só libera esse espaço de nomes para quem prova controle do domínio por DNS ou HTTP.
- Estadorespondeverificado em 2026-10-26
- Ferramentas80
- O servidor se chamaechorelay-mcp
- Versão do servidor1.15.0
- Versão do protocolo2025-06-18
Em 2026-10-26 o servidor respondeu a initialize e tools/list sem login. Primeira resposta em 758 ms.
- Ainda não avaliamos se as ferramentas fazem o trabalho do produto.
- Verificado em 1 dos 7 dias necessários para julgar a confiabilidade.
Depois de conectar
- publish_line_draft, cancel_line_publish, set_burst_opt_in, set_rpm_ceiling, set_outbound_allowlist alteram dados sem login: qualquer pessoa com o endereço pode chamá-las.
- As definições ocupam cerca de 29953 tokens de contexto: ative só as ferramentas de que a tarefa precisa.
Dito por regras a partir das medições acima. A primeira chamada provável é a escolha de um modelo na lista de ferramentas; leia a descrição antes de confiar nela.
- Nota INITE MCPdepois de uma semanaa nota precisa de 7 verificações diárias: 1 até agora
- Respondeumedindo1 das 7 verificações diárias necessárias para mostrar a porcentagem
- Mediana da primeira resposta816 ms
- Espaço no contexto do agente≈ 29.953 tokensas definições de todas as ferramentas (80), que o agente carrega a cada turno
- Definições das ferramentasA · 98 de 100
- Resultados tipados0 de 80 ferramentasdeclaram outputSchema: o resultado chega tipado e é lido de uma vez
- Parâmetros sem descrição: em 10 de 80
O que um agente consegue fazer com ele
- consegue · rename fields between your app and a partner API
- incerto · publish mapping edits without downtime or deployment
- incerto · fan one event out to several target APIs
Cada caso de uso do produto foi perguntado ao Jev junto com a lista de ferramentas deste servidor: um agente consegue fazer isso com essas ferramentas?
Vale conferir
- Ferramentas que alteram dados, em um servidor que responde sem login: publish_line_draft, cancel_line_publish, set_burst_opt_in, set_rpm_ceiling, set_outbound_allowlist
Um programa verifica o servidor uma vez por dia: initialize e tools/list, sem modelo. Os tokens são o tamanho das definições, a cerca de quatro caracteres por token. A nota é a média de seis verificações do nome, da descrição, do esquema e das anotações de cada ferramenta; diz se as ferramentas estão bem descritas, não se funcionam. A nota pesa só o que foi medido: se responde (25%), se faz o trabalho do produto (25%), definições (20%), contexto (10%), uso (10%) e a facilidade de conectar (10%). Uma parte não medida fica de fora, e uma instrução oculta limita a nota a 40. O estado dos servidores MCP dos fornecedores: método e números →
get_projectGet the EchoRelay project this token is scoped to: id, slug, name, caller-facing API base URL, whether the token has edit access, and the request-log hot-tier retention window.
list_linesList every line in the project: returns `{lines: []}` in one call, with no paging. Each entry reports `lineKey`, `name`, `active`, `docsShared`, `publishedAt`, `endpointCount`, and its draft state (`draftRevision`, `hasDraft`…
list_endpointsList the endpoints under one line, identified by `lineKey`; returns `{lineKey, endpoints: []}` with no paging. Each entry reports `id`, `name`, `path`, `httpMethod`, `strict`, `mock`, and `targetCount` — not the endpoint's full body…
get_endpointGet one endpoint's full document by `lineKey` and `endpointId`: `id`, `lineKey`, `name`, `url`, `httpMethod`, `strict`, `rateLimit`, `allowedIPs`, `idempotencyEnabled`, `senderSignature` (`{scheme, credentialId}`, plus `custom` for the…
get_configGet the project's published relay configuration — the exact JSON the EchoRelay Framework consumes. Includes pendingPublish with its frozen, redacted config when one is scheduled.
config_diffPreview what Save & Publish (or the pending scheduled publish, if one exists) would change: added/removed/changed lines, and within each changed line the added/removed/changed endpoints and targets, plus any project-level setting change…
list_config_revisionsList every retained revision of one line, newest first, so a target revision can be picked for rollback_config. Returns `{revisions: []}` with no paging; each entry has `revision`, `publishedAt`, `current`, and `active`. Errors when…
get_line_draftRead one line draft, its optimistic revision, preview, and schedule.
preview_line_draftPreview one line draft without publishing it.
publish_line_draftPublish one line draft now and clear only its schedule.
discard_line_draftDiscard every unpublished change and schedule for one line.
discard_draft_endpointDiscard one endpoint change from a line draft.
schedule_line_publishSchedule one non-empty line draft. Active subscribers required.
cancel_line_publishCancel one line schedule before its two-minute lock.
rollback_configPreview or apply publishing a retained line revision over what is currently published, clearing any pending schedule. Without confirmRevision this only returns the diff (the redacted change-gate preview, same shape as config_diff) between…
get_billingGet the project's credit balances (paid + testing) and which ledger it settles on. `billingModel` is `prepaid` (metered against the credit balance) or `invoiceable` (an Enterprise account, settled on the contract — its credit fields read…
set_burst_opt_inEnable or disable the auto-decaying burst window for live traffic and publish the change immediately. When enabled, brief spikes a little above your steady RPM cap are absorbed at the normal credit rate (no surcharge, no burst SKU)…
set_rpm_ceilingSet or clear a self-set ceiling on this project's own effective live-traffic RPM (Traffic shaping) — for when your origin can't take the throughput your plan grants. Never plan-gated: the ceiling can only LOWER your effective RPM below…
set_outbound_allowlistNarrow the project's outbound host allowlist — the hosts a target may point at. The current list is on get_project as `outboundHostAllowlist` (empty means any public host). This tool may only narrow it: `patterns` must be a strict subset…
create_lineCreate a new versioned line. A new line has no endpoints, so creating one publishes nothing and serves no traffic yet — add an endpoint, which publishes the line with it. Draft mode requires draftRevision 0. Requires edit access.
delete_lineDelete a line and every endpoint under it, immediately or by staging the removal in the line's draft with commitMode "draft" and draftRevision (returns `{draft}`, discardable via discard_line_draft, instead of deleting right away). An…
activate_lineActivate and immediately publish an inactive line so it serves traffic again. Blocked at the active-line cap — deactivate another line first. Requires edit access.
deactivate_lineTake a line off the data plane immediately (callers get 404) without deleting it — endpoints/targets/config are preserved and it can be reactivated later. A deliberate action; live traffic is never auto-disabled. Requires edit access.
duplicate_lineCopy a line and all its endpoints/targets/rules into a new line key — build v2 from v1. The copy is saved inactive and remains off the data plane; edit it, then activate_line when ready. Requires edit access.
set_docs_sharedTurn the line's public OpenAPI docs on or off. When enabled, the line's spec is published at docs.{baseDomain}/{slug}/{lineKey} (and …/openapi.json); when disabled those URLs return 404. The `docsShared` field on each line read…
create_endpointCreate an endpoint under a line. Defaults to immediate publish; draft mode requires draftRevision. scheduledAt stages the line draft then schedules it. Requires edit access.
generate_line_draftGenerate a draft endpoint under a line from a sample inbound request and a description of the target: infers the inbound body schema from the sample, reads the target's method/URL/fields from an OpenAPI document (targetDocument) or a bare…
update_endpointUpdate an endpoint immediately or by staging the change in its line draft with commitMode "draft" and draftRevision; the patch is merged field-by-field onto the endpoint's current values, so omitted keys keep their values. Targets are…
delete_endpointDelete an endpoint and its targets, immediately or by staging the removal in the line's draft with commitMode "draft" and draftRevision (returns `{draft}` instead of deleting right away). An immediate delete publishes a new revision…
default_endpoint_templateReturn a canonical minimal-valid endpoint JSON for a fresh line. POST it verbatim to create_endpoint to land an immediately-working endpoint, then customise. It comes back with `mock: true`: it answers callers with its own canned body and…
dry_run_endpointValidate an endpoint document without writing it. Returns either {ok: true, resolved: <Framework config slice>} or {ok: false, errors: {...}}. Pass endpointId to dry-run a PATCH against an existing endpoint; omit it to dry-run a create…
list_membersList accepted and pending members of this project, plus the owner (role "owner"), each with `id`, `email`, `name`, `role`, and whether the invite has been accepted. Returns `{members: [], count, seatCap, seatsUsed}` with no paging…
invite_memberInvite a person by email to collaborate on this project. Returns the new invitation record; the invitee receives an email with an accept link. Enforces the seat cap for the plan tier. Owner only.
remove_memberRemove a member (accepted or pending) from this project by memberId or email, matching the first record found; returns `{message, email}`. This deletes the membership record outright with no undo, so getting the person back onto the…
set_member_roleChange a member's role between editor, viewer, and billing. Identify the member by their member ID or email (from list_members); the project owner's own role cannot be changed. Returns the updated member record. Owner only.
resend_inviteRe-send the invitation email for a still-pending invite, by member ID or email (from list_members). The original accept link is reused. Already-accepted members are rejected. Owner only.
list_api_keysList the project's inbound API keys as metadata only — the secret plaintext is never returned, only `id`, `name`, `mode`, `prefix`, `createdAt`, `createdBy`, `lastUsedAt`, `expiresAt`, `revokedAt`, `successorId`, `predecessorId`, and…
create_api_keyMint an inbound relay (data-plane) API key for callers to send traffic to this project. Its `er_live_` or `er_test_` secret authenticates relay requests; it cannot call management MCP or REST. Returns the plaintext exactly once — store it…
rotate_api_keyMint a linked successor for an existing key. Returns the successor plaintext exactly once — store it now. The predecessor stays valid through its overlap window so callers can swap without downtime. Owner anywhere, editor on own keys.
reveal_rotation_successorOne-shot retrieval of the plaintext for a successor minted by the auto-rotation scheduler (not by rotate_api_key — that returns its own plaintext directly). Decrypts the at-rest ciphertext, returns it once, then destroys it; a second call…
revoke_api_keyRevoke a key immediately: it stops authenticating as soon as the change reaches the relay, with no overlap window, so callers still using it start failing. To replace a key without downtime, use rotate_api_key instead; if the key already…
get_key_policyReturn the project's key policy: `defaultKeyTtlDays` (what create_api_key uses when `ttlDays` is omitted), plus `maxKeyTtlDays` and `editorsMayCreateNonExpiringKeys`, the limits create_api_key enforces when minting a key. Read-only; use…
set_key_policyOwner-only. Edit the project's key policy. Only fields present in the patch are touched. Editors calling this get an error — use get_key_policy to read.
list_credentialsList the project's saved credentials — reusable target-auth secrets that can be referenced from any number of targets instead of entering auth inline per target. `auth` is redacted (secret fields never returned, even encrypted — see…
create_credentialSave a new reusable credential, sealed with the project's encryption key at write time. Neither this call nor any later read ever returns the secret back — reference it from a target by id (see create_endpoint/update_endpoint's…
update_credentialRename a credential and/or rotate its secret, publishing the change immediately so every target that uses this credential picks it up right away. Omit a secret field (or the whole `auth` object) to keep the existing value — the vault can…
delete_credentialDelete a saved credential. Blocked (not a permission or not-found error — a validation error) while any target still references it; repoint or remove those targets first.
list_requestsList inbound API requests the relay has processed for this project, newest first. Hot-tier window is the project's requestLogRetentionDays (see get_project). Optional filters narrow the result. Returns {total, limit, offset, rows[]} where…
get_requestGet one inbound request envelope + every per-target delivery attempt made on the way out (success / permanent_failure / retry_scheduled / dlq). The request and each attempt carry configVersion, the published config that authorised them; 0…
get_receiptsGet every target this request fanned out to, each with its delivery receipt or the reason it has none. A still-moving delivery (queued/retrying) answers from the live tracking copy, a terminal one (delivered/failed) from durable storage…
get_metricsAggregate request metrics for this project over a time window — volume, error rate and p50/p95/p99 latency, bucketed for charting. By default the series cover inbound requests; pass `targetId` to slice over one outbound target's…
list_dlqList entries currently in this project's dead-letter queue, newest first. One inbound request fans out per-target, so a single request may produce several DLQ entries, one per target that didn't accept it (different `targetId`s). Returns…
get_dlq_entryGet DLQ entries by entry id (`{ms}-{seq}`, as returned by list_dlq's `id`) or by `requestId`. `requestId` is the durable handle — stable across a retry, unlike `id`, which changes every time an entry is replayed and later dead-letters…
retry_dlq_entryRe-enqueue a DLQ entry to the main relay stream and delete it from the DLQ. A replay is billed like any relay — it charges the entry's original credit cost to the project before re-sending; if the balance is too low the entry stays in the…
discard_dlq_entryPermanently delete a DLQ entry without retrying it: the delivery is never re-sent and the entry cannot be restored. Use retry_dlq_entry instead when the delivery should still reach its target. The inbound request stays answerable through…
list_subscription_plansList the available subscription plans (Free, Pro, Scale) with monthly EUR price, credit allowance, per-project RPM cap, and how many active projects the plan includes. Read-only.
list_credit_packsList the prepaid credit packs available to purchase, returned as a bare array of `{credits, eurCents, usdCents, plnGrosze, welcomeEligible}` objects — not wrapped in an envelope, and not paginated (the whole catalog every time)…
list_addonsList the optional add-on subscriptions (RPM upgrades, extra team seats, extended log retention, extra file-delivery storage in +5 GB blocks, …). Each entry is monthly, renews every 30 days until cancelled, and carries `scope` (per_account…
get_subscriptionGet the project owner's current subscription: plan, active flag, period start/end, cancel-at-period-end flag, external Paddle subscription id, and whether a payment method is on file at the provider. Owner-only; requires a token minted…
preview_plan_changePreview what would happen if change_plan were called with this plan: the immediate-charge amount (cents), the next-invoice amount, the effective date, and the kind (`applied` for in-cycle upgrade, `scheduled` for at-period-end downgrade /…
As primeiras 60 de 80, na ordem do servidor.
Como conectar
Adicione o servidor à configuração do seu cliente MCP. Claude Desktop, Cursor e a maioria dos outros clientes leem este formato:
{
"mcpServers": {
"management": {
"type": "http",
"url": "https://mcp.echorelay.dev"
}
}
}Adicionar
Claude Code, no terminal
claude mcp add --transport http echorelay https://mcp.echorelay.devAdicionar ao CursorAdicionar ao VS Code
claude.ai, ChatGPT e outros clientes: adicione https://mcp.echorelay.dev como conector personalizado nas configurações.
Cada linha é algo que um programa encontrou ao procurar: o registro, a resposta do próprio servidor, uma especificação que se lê. Linha ausente quer dizer que não encontramos, não que não exista.
Cookies
Antes de contar esta visita
A análise e a medição de anúncios nos dizem quais páginas e quais dos nossos anúncios cumprem seu papel: Google Analytics e Google Ads, o pixel da Meta, Yandex Metrica e um identificador próprio. Nada é armazenado até você responder, e recusar não muda nada no site.