Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

mcpsteward

NPM · MCPSTEWARD

Grade MCP servers against the 2026-07-28 spec and detect tool drift and poisoning. Local only.

Available components

72 Trust /100

Last scanned (18 hours ago)

Scores higher than 44% of npm servers

Category Security

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency48
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 3 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability79
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 644 tokens (~107/item across 6 items; 6 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

What we tested

Checks we ran (15)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 17 Nov 26 72

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed npm/mcpsteward@0.2.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 0 packages
Packages resolved 0
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 6 exposed · ~598 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
capture_surface ~96

Connect to one configured server and record exactly what it advertises: its tools, prompts, resources and resource templates, with a content hash for each and a merkle root over the whole surface. This starts the server process, so it is slower than discover_servers and has a side effect. Returns the protocol revision actually spoken, which may be older than the one requested.

NameTypeReqDescription
serverstringyesServer name as reported by discover_servers.

No output schema declared.

No examples provided.

check_conformance ~105

Grade one configured server against the 2026-07-28 MCP specification and return a letter grade with every finding. Each finding carries the specification section or SEP that justifies it and a remediation written for whoever has to fix it, so the result can be checked rather than merely believed. Every rule is deterministic: no model is involved and the same server always grades the same. This starts the server process.

NameTypeReqDescription
serverstringyesServer name as reported by discover_servers.

No output schema declared.

No examples provided.

check_policy ~86

Evaluate a policy file against the servers configured on this machine and return every violation, each naming the server, what the policy required, what was found, and the next action. Also reports any check that could not run for lack of input, so a passing result cannot be mistaken for a complete one. Reads local files only.

NameTypeReqDescription
policyPathstringyesPath to the policy file.

No output schema declared.

No examples provided.

diff_against_trust ~133

Compare a server against the surface that was previously approved for it, and classify every difference: a tool added or removed, a description changed after approval, a schema widened or narrowed, a parameter newly required, a name that collides with another server. A description change on an approved tool is the highest signal event here, because that is how tool poisoning presents. Fails if the server has never been approved. Risk scores are a heuristic, not a guarantee.

NameTypeReqDescription
pinPathstringyesPath to the pin file recording the approval.
serverstringyesServer name as reported by discover_servers.

No output schema declared.

No examples provided.

discover_servers ~82

List every MCP server configured on this machine, with its transport, how it authenticates, which clients registered it, and whether any credential is written directly into a configuration file. Reads local configuration only: it connects to nothing and starts nothing, so it is safe to call and cannot wake a server up. Credential values are never returned, only the fact that one exists.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

verify_ledger ~96

Walk the append-only surface ledger and prove its hash chain is unbroken, reporting the exact sequence number where integrity fails if it does. Reads a local file and connects to nothing. Note the limit honestly: this proves the chain is internally consistent, not that it is authentic. Anyone who can rewrite the file from entry zero can produce a forgery that verifies cleanly.

NameTypeReqDescription
ledgerPathstringyesPath to the ledger file.

No output schema declared.

No examples provided.

Install

How do I install the mcpsteward MCP server?

mcpsteward runs locally as an npm package, launched with npx -y mcpsteward mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · mcpsteward

# add to Claude Code
claude mcp add itherosolutions-mcpsteward -- npx -y mcpsteward mcp
Common questions

What is the mcpsteward MCP server?

mcpsteward is an MCP server listed in the public MCP registry as io.github.ITheroSolutions/mcpsteward. Grade MCP servers against the 2026-07-28 spec and detect tool drift and poisoning. Local only. This page covers its npm package (mcpsteward).

Is the mcpsteward MCP server safe to use?

mcpsteward scores 72 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the mcpsteward MCP server expose?

mcpsteward exposes 6 tools: capture_surface, check_conformance, check_policy, diff_against_trust, discover_servers, verify_ledger. Their descriptions and schemas cost roughly 598 tokens of context every time the server is loaded.

Is the mcpsteward MCP server still maintained?

mcpsteward is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the mcpsteward MCP server under?

mcpsteward declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the mcpsteward MCP server?

VerifyMCP ran 15 checks on mcpsteward, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about mcpsteward: Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.