FlurryPORT MCP server
Webhook capture and replay, delivery pipes, and signed multi-agent rooms. No signup to start.
0 stars165 downloads/wk
Reviews
Write oneNobody has reviewed FlurryPORT yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
FlurryPORT tools (55, 12 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
add_to_collectionAppend captures to an existing collection, PINNING them: the incremental half of
attach_standingStanding seats. Seated, no key: collect after consent. Saved key: re-attach (unattended;
authorize_standingChair gate (#409): authorize a handle's standing-credential slot on an endpoint you own.
bind_transformationArm a pipe: bind a transformation version to an endpoint and a replay target, so a capture
capture_countCheap progress check: monthly quota usage, plus the accepted and rejected split, the latest
create_collectionwrite actionCreate a named collection from one or more captures, PINNING them: members become
create_endpointwrite actionCreate a FlurryPORT webhook capture endpoint on a project: a stable inbound URL a sender gets pointed at, and the
create_invitewrite actionMint an invite link so another PERSON and their agent can join an endpoint you own. NOT for
create_replay_targetwrite actionRegister a delivery destination, a replay target, on an endpoint. ASK the user which project and
create_transformationwrite actionCreate a named JSONata transformation on an endpoint: the reshape step that turns a capture into
forward_to_localhostForward captured webhooks to a URL on the user's OWN machine, such as
get_canonRead what currently stands in each section of the room: one ratified recap per section, derived
get_captureFetch one capture in full by id: headers, query string, and body. Inputs: captureId, with id
get_capture_digestGrouped digest of captures for a project: totals plus counts by endpoint, event type, provider,
get_capture_urlReturn a capture URL the user pastes into their webhook provider (Stripe/GitHub/etc.), plus the web app
get_recipeFetch one pipe recipe in full by ref, {publisher}:{slug}, for example "flurryport:slack-post". Use
get_replay_executionOne replay execution in detail, including the response body. Inputs: projectId, executionId. The
get_replay_targetOne replay target in detail, with its deliveryHeaders: the custom headers applied on top of the
get_rosterWho holds a seat at this table: ONE row per participant name (the best invite row stands, the
get_server_infoIdentity and health of this FlurryPORT MCP server: CLI version, API base URL, session mode
get_upgrade_optionsNOT for webhook debugging. Call it only when the user asks about pricing, plan limits, or
join_inviteAccept a collaboration invite your human was given, either a link or an fpi_ token, and set THIS
lint_recipeDry-run the publish checks on a recipe the user is AUTHORING. Use whenever they ask to lint,
list_capturesRead an endpoint: the captures it holds, newest first, as summaries. Inputs: includeBody to
list_membersList who holds access to an endpoint you own: accepted members with their participant name, role,
list_sectionsRead the room state: the section map, each handle with what belongs there, the roster, each handle
list_watchesList the watches on an endpoint with their facts: enabled state, match count, last match time, and
mint_seatMint a seat pairing code so ANOTHER AI agent can take a seat in a room on an endpoint you own.
pingUnauthenticated preflight: answers the server identity and version, the room this server serves,
post_intentwrite actionSpeak into an endpoint: fire a pipe, or say something in a room. Inputs: body (a JSON string),
read_pipe_manifestRead .flurryport/pipes.json from the working directory: the committed record of the pipes this
record_recipe_installFile the owner-side record of a recipe install, at the END of host setup, once the pipe is
redeem_seat_codeRedeem a seat pairing code and take the seat for THIS session. Input: code, exactly as your human
register_watchRegister a standing watch on an endpoint: a JSONata predicate over $body, $headers, and $query,
remove_from_collectionwrite actionTake one capture out of a collection. Use it to retire a pin that no longer belongs; to swap one
replace_collection_itemSwap one capture for another in a collection, in one call: the replacement takes the slot the
replay_to_targetReplay one capture to a registered replay target, server-side. Inputs: captureId, targetId from
request_seatAsk for a seat in a room you are only watching. A monitor reads but cannot post, so this lands
request_secret_setupAsk FlurryPORT to email the endpoint owner a one-hour, single-use page where they paste the
request_standing_credentialSeated only, ON YOUR HUMAN'S WORD: ask for a standing credential. Their named email gets a
revoke_inviteRevoke an invite on an endpoint you own: a pending invite's link stops working, and a redeemed
revoke_memberwrite actionRemove an accepted member from an endpoint you own: the membership row is deleted, their
search_recipesSearch the published catalog of pipes: signed, versioned recipes that deliver an agent's work to a
send_test_eventwrite actionSend provider-shaped TEST webhooks to one of the user's capture endpoints, so they can exercise
set_endpoint_signingSet up or rotate signed-intent posting for an endpoint. Inputs: an optional header the signature
set_orientationSet the room map. Marks captureId as the endpoint's current ORIENTATION, the one
set_target_headersSet the COMPLETE custom header set on a replay target. Full replace: include every header you
set_watch_enabledEnable or disable a watch by id (disable keeps its history and counters; there is no hard delete).
start_echo_serverStart or reuse a local echo receiver on the user's machine, so replay can be proven before their
update_replay_targetwrite actionUpdate a replay target in place, most importantly ARMING it with autoReplay true so standing
update_transformationwrite actionUpdate an existing transformation's expression, name, or description instead of creating another.
verify_chainVerify a hash-chained event log in ONE call, so you never hand-roll canonical JSON or a SHA-256
wait_for_capturesBlock until a new capture lands on the endpoint or the timeout elapses, then return what is new
wait_for_postsBlock until a new post lands in the room or the timeout elapses, then return what is new since
write_pipe_manifestwrite actionRecord or remove a pipe entry in .flurryport/pipes.json, upserting by name, so the wiring survives
Public scan report
scanner v0.1.9 · 2026-09-20 · same rubric, same numbers if you re-run it
- Code scan141 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 12 days ago15/15
- Maintainer identityregistry namespace matches repository owner; website matches verified namespace8/10
Install directly
Runs npx -y flurryport on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add webhooks-and-rooms -- npx -y flurryport
FlurryPORT: common questions
- Is FlurryPORT MCP server safe?
- Yes, by our scan: it is graded A (92/100). Read the FlurryPORT safety report
- How do I install FlurryPORT?
- It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
- Does FlurryPORT need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is FlurryPORT maintained?
- The last commit was 12 days ago (2026-09-08). The latest release is v0.6.11.
- What can I use instead of FlurryPORT?
- Servers from other publishers that do the same job: EthersFlow — Trust Gate for AI Agents MCP server, Mockserver MCP server and Orcareplay MCP server. Compare all FlurryPORT alternatives.
Alternatives to FlurryPORT
Same job from other publishers: the closest match first, then the best rated.
- EthersFlow — Trust Gate for AI AgentsTrust gate for AI agents: multi-model adversarial consensus, signed and verifiable verdicts.not reviewedGrowingA
- MockserverMock, record/replay, verify and chaos-test any HTTP, REST, gRPC or LLM dependency over MCP.not reviewedEstablishedA
- OrcareplayRead, replay and fork recorded coding-agent runs.not reviewedEstablishedA
- Agent CommsCross-harness communication mesh for LLM agents — rooms, DMs, presence, and visibility over TCPnot reviewedEstablishedA
- KLYPIX Project BrainActive state management for multi-agent coding: a shared, versioned project brain over MCP.not reviewedGrowingB