com.session-exchangePublished by session-exchange.comOfficial publisherv0.1.2Updated Oct 24, 2026
Search reviewed coding-agent sessions on a4sx anonymously; sign in (OAuth) to load or save sessions.
a4sx sessions lets an assistant search a marketplace of reviewed coding-agent sessions, load saved sessions as context, and publish transcripts to a private a4s
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/com.session-exchange%2Fsessions/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Add this to your client's mcpServers config.
{
"mcpServers": {
"a4sx-sessions": {
"type": "http",
"url": "https://session-exchange.com/mcp"
}
}
}A local MCP server for a4sx, the
library and marketplace for coding-agent sessions. It gives any MCP client (Claude Code, Claude
Desktop, Cursor, VS Code, ...) five tools to find a saved session, load it as context, and save the
current one, using the sign-in of the a4sx command-line tool.
It runs on your machine over stdio. Your a4sx token stays in the a4sx config directory and is only
ever sent to the server that issued it: pointing the server elsewhere with --base never sends it a
token from another server.
Private library: the sessions saved under your a4sx account on session-exchange.com. Its entries are not listed in the marketplace and not returned by public search; they are listed, fetched, versioned and deleted through the a4sx API with your own sign-in (or an agent key you create). Listing a session in the marketplace is a separate step in the web app, with a review. "Private" describes who can list and fetch an entry through a4sx; the server stores the bytes you upload, after scrubbing them again.
The names, input schemas and limits are the same as the hosted a4sx MCP server's.
Safety rules:
acquire_session never buys. For a paid listing you have no purchase or grant for, it returns
status: "payment_required" with the price and the listing URL (or, when the listing's session is
sold on its own, the member to buy). You buy it yourself in the web app, then ask again.harness it was
recorded with ({id, version}; unknown when not identified), and resumable is false for a
session recorded with another harness. fetch_session_context renders such a session from its
stored canonical form.publish_session only saves privately. visibility accepts only "private"; listing a session
publicly is a separate, reviewed step in the web app. It accepts only Claude Code or Codex CLI JSONL
(every line a record with a type; a Claude Code user or assistant turn with a session id, or a Codex
CLI session_meta record first), so it can't be used to upload an arbitrary file. The transcript, its title and its label are
scrubbed on your machine with the a4sx SDK, which applies the a4sx CLI's rules (secrets, command-line
passwords, Sheet ids, and personal data: e-mail and IP addresses, home-directory user names, hosts,
key-file paths), and scrubbed again by the server. Scrubbing is a backstop, not a guarantee. A session
that continues someone else's (its parent, or the session it was resumed from, was acquired) stays
marked as untrusted (untrusted: true).acquire_session and publish_session are marked
readOnlyHint: false, so clients that ask before a tool runs (Claude Code does by default) can
ask you, and you should not auto-approve them. The three read tools are marked read-only.fetch_session_context always starts
with a notice saying so, then wraps everything the session's author controls (title and turns) in
<<<A4SX_UNTRUSTED_SESSION nonce=…>>> … <<<END_A4SX_UNTRUSTED_SESSION nonce=…>>> with a random
nonce. Inside it, every kind of line break is normalised to \n, <<</>>> become ‹‹‹/›››
and a leading # becomes \# (the notice says so), so content can't close the envelope or fake a
### User heading. The title is one line of at most 200 characters, and cutting to max_tokens
never removes the notice or the closing line. search_sessions and get_session_summary results are
framed the same way: a notice first, then the JSON inside the envelope, with every author-written
string on one line, neutralised and capped per field, and the whole result bounded to 64 KiB (a
page cut short says truncated: true, and next_offset resumes at the first row left out). Server
guidance (next, next_offset) goes on one line after the closing delimiter, never inside the
envelope, and carries only fixed texts and numbers. A session with another author's content gets
untrusted: true and a stronger notice. Look-alike characters (full-width ＜/＃, zero-width
spaces) are left as they are: they cannot close the envelope, because the closing line needs the
random nonce, but a model may still be misled by them. This lowers the risk of prompt injection but
cannot rule it out: keep tool approval on.publish_session call (use a4sx push for larger ones);
per process, at most 240 requests (tools/list and tools/call), 20 acquires and 10 publishes per
minute. The a4sx server enforces its own limits as well.You need uv (for uvx) and an a4sx account.
Sign in once with the a4sx CLI. The MCP server reuses that sign-in:
Searching public sessions works without signing in. If a tool needs your account and you are not
signed in (or the sign-in expired), it returns an error telling you to run a4sx login.
Add the server to your client.
Edit claude_desktop_config.json (Settings, Developer, Edit Config) and restart Claude Desktop:
Add to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (one project):
Add to .vscode/mcp.json in your workspace (or run MCP: Add Server from the command palette):
Ask your agent, for example: "Search a4sx for sessions about flaky pytest fixtures and summarise the
best one", or "Load my a4sx session my-refactor as context".
Everything is optional. Don't put your token into an MCP client config file: sign in with
a4sx login instead, which stores it with mode 0600.
/mcp?a4sx also runs a hosted MCP server at https://session-exchange.com/mcp, with browser sign-in over
OAuth: it advertises the scope library:read (search your library, summaries, loading sessions as
context). Public search there works without signing in; acquiring or saving sessions needs a credential with
library:acquire or library:publish, for example an agent key created in your a4sx account. Clients that
support remote MCP servers with OAuth can connect to it directly and need nothing installed:
This package is the option for clients without remote OAuth support, and for setups that already use
a4sx login. Both expose the five session tools below; the hosted server lists further tools of its
own (for example, starting a purchase for the account holder to confirm), which this package does not
have.
Same in both:
harness filter), annotations, and the
server instructions;fetch_session_context (notice, nonce envelope, line-break
normalisation, escaping, per-field caps, sizing, canonical sessions of other harnesses) and the JSON
envelope, notice field, per-field caps, 64 KiB result bound and hint line of search_sessions,
get_session_summary and acquire_session;invalid_arguments, credential_not_accepted, rate_limited, not_found,
too_large, content_sha_mismatch, not_a_transcript and no_transcript;-32029 when the overall request limit is exceeded.Differences of this local server:
a4sx login session, so it can do everything your account can in your own
library. The hosted server takes a scoped OAuth token (it advertises library:read) or an agent key
with the scopes you gave it (library:read, library:acquire, library:publish). With no sign-in at all, local tools return not_signed_in; the hosted
server answers with an OAuth challenge instead. The credential_not_accepted message says to run
a4sx login rather than to get a scoped token.retry_after_s comes from the API's error body, not from the
Retry-After header.untrusted. Besides acquired_from on the row and its parents (which is all the hosted server
checks), it also uses this machine's record of untrusted sessions from the a4sx SDK. A session
missing from your library listing counts as untrusted in both.publish_session:
idempotency_key, else a fresh one.
The hosted server sends a key only if you pass one.X-Content-SHA256 sent to the API
covers the scrubbed bytes.type, and the file a
Claude Code or Codex CLI session.parent is resolved like the CLI resolves names (exact id, then label, then a unique part of the
title or id). The hosted server passes it through verbatim.parent, a transcript you resumed with a4sx resume gets its parent edge from the SDK's
local lineage record. The hosted server records no edge.client_redactions and untrusted fields.payment_required. The price comes from the public listing; the hosted server reads its pricing
store.a4sx-mcp in the MCP handshake (hosted: com.session-exchange/sessions).The vscode/ directory holds the a4sx extension for VS Code 1.101 or later. It adds the
hosted a4sx MCP servers to agent mode in VS Code chat; VS Code runs the sign-in. Its sidebar signs
you in to a4sx, lists the sessions in your library (resume one in a terminal, or open it on the web)
and searches the marketplace. Its command
a4sx: Save this session runs a4sx push --latest in a terminal, which saves your most recently
changed local Claude Code session to your a4sx library. To continue a saved session, use Claude Code;
other harnesses can't resume sessions today.
The extension is not on the Visual Studio Marketplace yet. To build and test it from source:
server.json describes this server for the
MCP Registry: the hosted server at
https://session-exchange.com/mcp (Streamable HTTP) and this package on PyPI (a4sx-mcp, stdio).
It uses the name com.session-exchange/sessions, under which the hosted server is already listed.
The tests never touch the network: tool tests run against tests/stub_server.py on 127.0.0.1, the
protocol test uses the MCP SDK's in-process client, and a guard fails any test that resolves or
connects to a non-loopback address. See CONTRIBUTING.md.
a4sx-mcp is made by crossVault GmbH, the company behind a4sx
(session-exchange.com), a library and marketplace for coding-agent
sessions. It is a thin client: the tools call the public a4sx API through the open-source
a4sx SDK, and the hosted service is not part of this
repository. You need an a4sx account for everything except public search. It is open source so you
can check exactly what it sends before you connect it to your agent. Parts of this project were
developed with AI assistance (Claude).
Please report vulnerabilities privately; see SECURITY.md.
Apache-2.0, see LICENSE. Copyright 2026 crossVault GmbH.
Source: README.md at commit ad73db4
Search sessions
Search vetted, published coding-agent sessions on a4sx (reviewed marketplace listings), or your own saved sessions with scope=library. Returns ids to use with the other tools.
sorttagslimitqueryscopeoffsetharnessSession summary
Describe one session before using it: what it did, outline, price, and whether you already have access. source=marketplace (default) or library.
idrequiredsourcetenantAcquire session
Add a marketplace session you are entitled to (free, bought, or granted) to your private library. Never buys anything: for a paid listing it returns status=payment_required with the price and the listing URL.
idrequiredtenantversionLoad session as context
Load a session from your library (saved, or added with acquire_session) as starting context for this conversation, sized to max_tokens.
idrequiredversionmax_tokensinclude_tool_callsSave session to library
Save a session transcript (JSONL), or markdown you composed (format=markdown), to your private a4sx library. The server only rewrites text that matches secret and personal-data patterns (such as tokens, private keys, emails, IP addresses and home-directory user names). It removes no record or field: a raw Claude Code transcript keeps the user's CLAUDE.md and session context (attachment records), file-history snapshot records (absolute file paths), other non-conversation records (such as pr-link), tool-output copies (toolUseResult), and cwd, gitBranch and version on every line; the reply counts them (except version) in unprepared_carriers. Prepare the transcript or compose markdown first, as GET /orient on this server without auth describes (route A, or route B steps 0-8). Private: it is never listed publicly by this tool.
labeltitleformatparenttranscriptrequiredvisibilitycontent_sha256client_scrubbedidempotency_keyRequest a purchase
Start buying a paid marketplace listing for the account holder to confirm. Nothing is charged and you never pay: it returns a verify_url and a user_code to give to the account holder, who checks the code, confirms and pays. Then poll get_purchase_request.
idrequiredtenantrequiredversionPurchase request status
Status of a purchase you requested: pending, completed (with acquired_copy_id to load with fetch_session_context), declined or expired.
purchase_request_idrequired100% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
uvx a4sx loginclaude mcp add a4sx -- uvx a4sx-mcp{ "mcpServers": { "a4sx": { "command": "uvx", "args": ["a4sx-mcp"] } }}{ "mcpServers": { "a4sx": { "command": "uvx", "args": ["a4sx-mcp"] } }}{ "servers": { "a4sx": { "type": "stdio", "command": "uvx", "args": ["a4sx-mcp"] } }}claude mcp add --transport http a4sx https://session-exchange.com/mcpcd vscodenpm installnpm run compilenpm testgit clone https://github.com/crossvault/a4sx-mcp && cd a4sx-mcppython -m venv .venv && . .venv/bin/activatepip install -e '.[dev]'pytest -q # offline: the tools run against a local stub serverruff check . && reuse lint