mcpwatch MCP server
io.github.Sreelal727/mcpwatch·v0.4.1Records MCP tool calls and itemises the token cost each server adds to your context.
0 stars47 downloads/wk
Reviews
Write oneNobody has reviewed mcpwatch yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
mcpwatch tools (5)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
find_callsSearch recorded MCP calls by tool name, server, status, or free text inside the request/response payloads.
get_callReturn the complete recorded request and response JSON for one call id (the [#123] shown by the other
recent_failuresShow MCP tool calls that recently failed, with the error message and the arguments that caused them.
server_healthHealth of every MCP server on this machine: call volume, error rate, latency, crashes (with the server's
token_costsItemise what the user's MCP servers cost in context tokens: the per-session tax each server
Public scan report
scanner v0.1.10 · 2026-10-15 · same rubric, same numbers if you re-run it
- Code scan32 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 41 days ago12/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How mcpwatch compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 88/100
- higher than 75% of 48,243 servers
- Tools
- 5
- the typical server has 7
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 47
- more than 37% of 12,306 servers with a package
What its tools let an agent do: 5 read
Install mcpwatch in Claude Code, Cursor or VS Code
Runs npx -y @sreelal727/mcpwatch on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add mcpwatch -- npx -y @sreelal727/mcpwatch
What the publisher says
From the mcpwatch repository's README, as published. We do not edit it. Read it on GitHub
👁 mcpwatch
Every MCP server you've installed is charging you tokens on every single session. See the bill — then cut it.
mcpwatch records the real traffic between your coding agent (Claude Code, Codex, Cursor, Claude Desktop) and your MCP servers, then itemises what that setup actually costs you in context — and tells you exactly what to delete.
One command. All local. Zero config. No account, ever.
<!-- demo.gif goes here before launch: record with scripts/seed-demo.ts --keep-running + mcpwatch ui -->
Here's what nobody tells you when you install an MCP server: its tool definitions get injected into your agent's context at the start of every single session, whether you use that server or not. A big vendor integration with 50 tools can cost you 15,000+ tokens before you type a word. You pay it again on the next session, and the next.
On top of that you're paying for tool responses that return 200 kB when you needed one row, calls that fail and get retried, and agents re-fetching things they already had.
None of it shows up anywhere. mcpwatch records the actual bytes on the wire and turns them into an itemised bill.
See your number in ten seconds
No setup, no restart, no waiting. This starts each MCP server you already have configured, asks it for its tool list the way your client does, measures it, and shuts it down:
npx @sreelal727/mcpwatch auditEvery new session pays ~9,262 tokens ($0.05) to load these tool definitions,
before you type a word:
github 8,825 tokens 52 tools 95% Cursor
filesystem 437 tokens 6 tools 5% Cursor
9,262 tokens every session
At 10 sessions a day that is ~2,778,600 tokens a month ($13.89 at $5/M) spent
before any work happens.
"github" alone is 95% of that. If you do not use it in every project, moving it to
the projects that need it is the single biggest win available to you.That's the fixed cost, and it's knowable without recording anything.
Then find out what you actually use
Which of those tools you call does need real traffic. Instrument once, work normally for a day, and ask:
npx @sreelal727/mcpwatch init # then restart your client
npx @sreelal727/mcpwatch cost # a day laterYour MCP setup costs ~12,486 tokens per session before you type a word ($0.06 at $5/M tokens).
PER-SESSION TAX — tool definitions loaded into every new session:
github 10,762 tokens 46 tools, none used ← never called
filesystem 780 tokens 8 tools, 2 used
postgres 944 tokens 9 tools, 1 used
12,486 tokens, every session
AT YOUR ACTUAL PACE — 34.9 server startups/day over 11.3 days:
~4,362,755 tokens/month ($21.81) on tool definitions alone, before any work happens
~4,939,089 tokens/month ($24.70) all inShortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
mcpwatch: common questions
- Is mcpwatch MCP server safe?
- Yes, by our scan: it is graded A (88/100). Read the mcpwatch safety report
- How do I install mcpwatch?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does mcpwatch need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is mcpwatch maintained?
- The last commit was 62 days ago (2026-09-04). The latest release is v0.4.1.
- How does mcpwatch compare with other MCP servers?
- safety score 88/100 (higher than 75% of 48,243 servers); tools 5 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.