Bragproof

← Reports

mcpspan-mcp

Starts with no setup0.15.0npm

Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.

Needs to start: nothing
Returns a result when called with no setup: 0 of 5 tools tried
Contacts while installing and starting: nothing

13tools listed
0hosts contacted
0files written
0.1 sto start
3dependencies

Its tool definitions changed since version 0.14.0. If you approved the earlier ones, read them again.

What it contacted

Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.

Starting it

npx -y mcpspan-mcp@0.15.0

Installing a package runs its code. Use a sandbox for anything you have not read.

Calling its tools

5 tools that take no input and look read-only were called once with nothing. 0 returned a result.

list_serversNo usable answer tool reported an error: MCPSPAN_READ_TOKEN is not set. Make a read token in mcpspan, under Settings → Read tokens, and give it to this MCP server.
get_overviewNo usable answer tool reported an error: MCPSPAN_READ_TOKEN is not set. Make a read token in mcpspan, under Settings → Read tokens, and give it to this MCP server.
list_toolsNo usable answer tool reported an error: MCPSPAN_READ_TOKEN is not set. Make a read token in mcpspan, under Settings → Read tokens, and give it to this MCP server.
list_errorsNo usable answer tool reported an error: MCPSPAN_READ_TOKEN is not set. Make a read token in mcpspan, under Settings → Read tokens, and give it to this MCP server.
list_unknown_toolsNo usable answer tool reported an error: MCPSPAN_READ_TOKEN is not set. Make a read token in mcpspan, under Settings → Read tokens, and give it to this MCP server.

During the calls it contacted nothing it had not already contacted.

Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.

What its tools tell an agent

In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.

Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.

Tools

list_servers
The MCP servers this mcpspan account reports on, with their names and ids.
get_overview server, days, from, to, client
Calls, failures, error rate, response times (median and 95th percentile) and the share of each client, for one server over a window.
list_tools server, days, from, to, client, sort, limit
A server's tools ranked by calls, errors, response time or name, each with its calls, errors, error rate and response times.
get_tool server, days, from, to, tool
Everything recorded about one tool: why its calls failed and the commonest error messages, which arguments the server refused, its parameters, how large its answers are, when its definition changed, how often agents repeated a call, and which call came right before the ones that repeated or failed.
list_errors server, days, from, to, client, tool, limit
The most recent failed calls, newest first: which tool, which client, when, what kind of failure (a handler that threw, a tool that answered with an error, refused arguments, an unknown tool) and the error message when the server records them.
8 more tools
list_unknown_tools server, days, from, to
Tools that agents asked for but the server does not have: how often, which clients, the closest tool the server does have, and what the agent did next.
list_clients server, days, from, to
The clients that called the server (Claude, Claude Code, Cursor, VS Code, ChatGPT and others), each with its calls, error rate and response times.
compare_versions server, days, from, to, client
The server's versions in the window, newest first, each with when it was first seen, its calls, error rate and response times: how a release compares with the one before.
get_release_report server, client, version
Did a release make things worse: one server version against the one before it. The new version's calls from its first one (releasedAt), for up to 7 days or until a newer version came, against the previous version's calls over a period as long right before it. verdict is worse, same, better, too-early (under 50 calls on a side) or first (no earlier version); worse means errors rose by more than a point and more than chance, or p95 slowed by a quarter. Also: tools with their numbers either side, worst change first (definitionChanged when the description or schema changed with it; refused counts calls whose arguments the schema refused), newFailures (kinds of failure the previous version did not have), agents (what became of sessions either side), clients (share of calls either side; clientsShifted when the mix moved enough to change the numbers), and otherVersionCalls (calls after the release from another version).
get_tool_listing server, days, from, to, client
Every tool as agents were shown it when they listed the tools: in how many sessions, how many of those called it, and how large its definition is. Finds tools agents see but never use, and definitions that cost context.
list_sessions server, days, from, to, client, tool, with, limit
Recent sessions (one connection each), newest first, with their calls, failures, tools used and calls an agent repeated with the same arguments.
get_where_agents_get_lost server, days, from, to, client, tool
Where agents got stuck and what they did about it. A time stuck is a failed tool call and the retries of the same tool straight after it; each ends recovered (the tool then worked, with meanRetries retries on average), wentElsewhere (the agent called something else, insteadMostOften), endedOnIt (the session stopped there, nothing for 30 minutes) or undecided (too recent to tell); looped counts those where a retry repeated the same arguments. Without a tool: every session by the worst that happened in it (clean, recovered, wentElsewhere, looped, endedOnFailure, undecided) and the tools agents got stuck at, worst first. With a tool: that tool's times stuck, as a whole and by client.
get_session server, days, from, to, session
One session's calls in the order the agent made them, with each call's outcome and error.

Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.

Install facts

LicenseMIT
Needsnode >=20
Sourcegithub.com/mcpspan/mcpspan
Install scriptsNone declared by it or anything installed with it.
Tarballsha512-2EImjWh+18Kgt0OvNUuF6WNhPVgCK6gTIj6tg/MMJnfc6cXhTilVjmC+WdgJ239Zyo1EWP1NM37LexpUzSImfg==

Versions reported

VersionRunResultTools
0.15.02026-11-16Starts with no setup13
0.14.02026-11-12Starts with no setup12

Check this report yourself

This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.

Show it on your README

Bragproof: Starts with no setup

[![Bragproof](https://bragproof.smaverk.com/badge/mcpspan-mcp.svg)](https://bragproof.smaverk.com/r/mcpspan-mcp)

New version out? Ask for a fresh report.