
EchoRelay MCP server
Which MCP servers are EchoRelay's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-26
- Registry namedev.echorelay/managementverified in the MCP registry
The registry name sits under echorelay.dev. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-26
- Tools80
- Server calls itselfechorelay-mcp
- Server version1.15.0
- Protocol version2025-06-18
On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 758 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 2 of the 7 days it takes to judge reliability.
Once connected
- publish_line_draft, cancel_line_publish, set_burst_opt_in, set_rpm_ceiling, set_outbound_allowlist change data without a sign-in: anyone with the address can call them.
- Its definitions take about 29953 tokens of context: enable only the tools a task needs.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
- Answeredmeasuring2 of the 7 daily checks it takes to print a share
- Median first answer816 ms
- Space in an agent's context≈ 29,953 tokensthe definitions of all its tools (80), which an agent carries on every turn
- Tool definitionsA · 98 of 100
- Typed results0 of 80 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 10 of 80
What an agent can do with it
- can do · rename fields between your app and a partner API
- not sure · publish mapping edits without downtime or deployment
- not sure · fan one event out to several target APIs
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
- Tools that change data, on a server that answers without a sign-in: publish_line_draft, cancel_line_publish, set_burst_opt_in, set_rpm_ceiling, set_outbound_allowlist
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
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 /…
The first 60 of 80, as the server listed them.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"management": {
"type": "http",
"url": "https://mcp.echorelay.dev"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http echorelay https://mcp.echorelay.devclaude.ai, ChatGPT and other clients: add https://mcp.echorelay.dev as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.