Name: walletlink.social
Author: walletlink

walletlink.social MCP

Resolve wallet addresses to X and Farcaster accounts, and back again.

Tool-list grade A Remote · Streamable HTTP OAuth 2.1 8 tools v1.4.0

No reviews yet by walletlinkGitHub The publisher’s own endpoint — this marketplace is not in the path

93/100

tool-list score

tools declared

remote

at its publisher

—

calls last 7d

What it does

Resolve wallet addresses to X and Farcaster accounts, and back again.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --transport http walletlink-social-mcp https://walletlink.social/api/mcp

# 2 — ask your agent for something these tools do
#   walletlink_resolve_wallets, walletlink_wallets_by_x_handle, walletlink_wallets_by_farcaster_username and 5 more

walletlink.social costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

walletlink1 server

1 category

All 1 server

Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.

Installation

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.

Claude Codedeclared by this listing

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. Its publisher asks you to sign in with OAuth: run /mcp in Claude Code and pick this server, and it opens a browser for that once.

claude mcp add --scope user --transport http walletlink-social-mcp https://walletlink.social/api/mcp

Reconnect, or start a new session, and the tools appear in the model’s tool list.

Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add — the only sign-in is its publisher’s own, with OAuth.

What it asks of you

Nothing is required, but it can take Authorization header (Bearer wts_live_... An API key from https://walletlink.social, self-serve for any signed-in account, free allowance included. Not needed by a client that supports OAuth: this server is an OAuth 2.1 resource, and a tool call with no credential answers 401 naming its protected resource metadata. Tool discovery needs neither.) if you want to set it.

What it writes

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.

What you approve

8 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.

Only tools that write or reach the network

Resolve one or more Ethereum addresses to the social identities attached to them: X handle, Farcaster account, ENS name, Lens profile, GitHub account. COST: one match credit per address that resolves to an X handle or a Farcaster account. An address that resolves to nothing is free, and so is one carrying only an ENS name, a Lens profile or a GitHub account. Up to 50 addresses per call on the def

Parameter	Type	Required	Notes
addresses	array	yes	Ethereum addresses, each 0x followed by 40 hex characters. Case does not matter.

Find the wallets in the index attested to an X account. The reverse of resolving an address. Only wallets whose recorded sources are all attested come back, so a wallet whose attested link sits beside a correlated source is left out; resolving that address still shows it, labeled. Needs a key that belongs to an account: a key bought with USDC alone gets ACCOUNT_REQUIRED. COST: one match credit pe

Parameter	Type	Required	Notes
handle	string	yes	An X handle, 1 to 15 letters, numbers or underscores. A leading @ is accepted. Case does not matter.
cursor	string	no	The next_cursor from a previous call, passed back unchanged. Omit for the first page.

Find the wallets in the index attested to a Farcaster account. Only wallets whose recorded sources are all attested come back, so a wallet whose Farcaster verification sits beside a correlated source is left out; resolving that address still shows it, labeled. Needs a key that belongs to an account: a key bought with USDC alone gets ACCOUNT_REQUIRED. COST: one match credit per wallet returned, an

Parameter	Type	Required	Notes
username	string	yes	A Farcaster username, such as dwr or vitalik.eth. 1 to 32 characters of letters, numbers, dots and hyphens, starting with a letter or a number.
cursor	string	no	The next_cursor from a previous call, passed back unchanged. Omit for the first page.

How much of the index carries each identity type. Use it to judge whether a lookup is worth making before making it. COST: free on both meters. It resolves no wallet and consumes no rate limit. A key whose balance is zero can still read the free endpoints; the balance and coverage reads keep answering at zero, and only a call that could bill refuses with NO_CREDITS. addresses_with_an_identity ov

No parameter schema on file.

How many match credits the configured key has left, and how much of the request allowance it has used. COST: free on both meters. Call it before a reverse lookup, which can spend up to 100 credits in one go. matches_available is the meter that stops a metered call: at zero, the resolve and reverse tools refuse, while this tool and the coverage tool keep answering, so a drained key can always rea

No parameter schema on file.

Submit a list of addresses as a background job. A job runs a deeper scan than the resolve tool: an address the index has not checked, or holds only stale answers for, is resolved against live sources, so a job can find identities the resolve tool reports as never seen. Use it for lists larger than one resolve call, or when misses are worth re-checking. COST: billed on matches exactly like resolvi

Parameter	Type	Required	Notes
addresses	array	yes	Ethereum addresses, each 0x followed by 40 hex characters. Case does not matter. The ceiling is the balance-derived cap, not a fixed number; a list over the cap is refused with the cap named.

Progress and results for a job submitted with walletlink_submit_job. While the job runs it reports processed counts; on completion it reports the resolved records and what was billed. COST: free on both meters, so a drained key can still collect results it already paid for. A field that is absent was not measured. Absent is not false: a missing reachability means the handle was not checked, never

Parameter	Type	Required	Notes
job_id	string	yes	The job id returned by walletlink_submit_job.
offset	integer	no	Result row to start from, for a completed job. Pass the next_offset from a previous call to continue. Omit for the first page.

A dry run over a list of addresses: how many are in the index, how many were checked and found bare, how many have never been seen, and the band a resolve would bill inside. Counts only, no identities. Use it to decide whether a list is worth resolving, and which tool to spend on. COST: free on the match meter, always, even at zero balance. It weighs the rate window exactly like resolving the sam

Parameter	Type	Required	Notes
addresses	array	yes	Ethereum addresses, each 0x followed by 40 hex characters. Case does not matter.

Free

$0 forever

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

Nothing here is billable: mcprush charges nothing to install walletlink.social or to call it, at any volume.

ATool-list grade · score 93 / 100

Release 1.4.0 · scanned 23 Oct 2026

Graded from the tools this server lists, not from its source code.

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.

Threat score100

Client score93

Findings0 threat · 0 capability

Capabilitymoderate

Coveragemanifest

Verificationnot in this report

Surface digest0c02bbfefc6ec780c31a9fe218b5fb76a3b19db35e0a93093e944caa86083753

Score vectorthreat 100 → client 93

Term	Level	What it prices	Points
capability-exposure	moderate	capability blast radius (moderate) — client exposure if the model is manipulated	−3
coverage-honesty	manifest	inspection depth (manifest) — how much of the target the scan could see	−4

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.

Tool surfaceread

Implementation sourcenot available

Package metadatanot available

Live transportnot available

The implementation source was not read — this reflects the declared tool metadata only.

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.

Tool	Capability tags	Why the tag was assigned
walletlink_resolve_wallets	state-write	state-write: declares readOnlyHint: false
walletlink_wallets_by_x_handle	state-write	state-write: declares readOnlyHint: false
walletlink_wallets_by_farcaster_username	state-write	state-write: declares readOnlyHint: false
walletlink_index_coverage	no tags
walletlink_account_balance	no tags
walletlink_submit_job	external-sink	external-sink: declares readOnlyHint: false, openWorldHint: true
walletlink_job_status	no tags
walletlink_estimate_list	no tags

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.

Supply chain and provenance

Integrityfirst-seen

Surface digest0c02bbfefc6ec780

Scanned2026-10-23

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.