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.

BRYDGE

NPM · BRYDGE-MCP

Checks whether an agent's actions actually happened, against the destination's own records.

Available components

0 this week 84 Trust /100

Last scanned (22 hours ago)

Scores higher than 75% 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
  • 0 of 3 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency45
Schema Quality & AI Usability73
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 874 tokens (~174/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
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
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 6 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
What we tested

Checks we ran (16)

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

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.

  • 19 Nov 26 0
    • Stability: 0.97 → pass security
  • 18 Nov 26 0
    • Stability: pass → 0.97 functional
  • 12 Nov 26 0
    • Stability: 0.97 → pass security
  • 11 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 8 Nov 26 −2
    • Stability: pass → 0.87 functional
  • 2 Nov 26 0
    • Stability: 0.97 → pass security
  • 1 Nov 26 0
    • Stability: pass → 0.97 functional
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/brydge-mcp@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 3 packages
Packages resolved 3
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 5 exposed · ~665 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
brydge_get_finding ~72

What BRYDGE has already found about an action, without reading the records again. Free. BRYDGE checks each action by itself once the destination's reporting window has passed; until then this says PENDING.

NameTypeReqDescription
authorizationstringyesThe authorization id brydge_supervise returned for the action.
NameTypeReqDescription
agentAgreedboolean|nullyes–
authorizationstringyes–
becausestringyes–
checkedAtstring|nullyes–
claimedstring|nullyes–
externalRefstring|nullyes–
reasonstring|nullyes–
replayedbooleanyes–
statestringyes–

No examples provided.

brydge_get_headroom ~80

How many actions of this kind you may take in any 24 hours before a person is asked, how many are left, and what raises or lowers that. Every report BRYDGE checks and finds true raises it.

NameTypeReqDescription
actionstringyesThe kind of work, as it is set up in BRYDGE, such as refund.
NameTypeReqDescription
actionstringyes–
actionsnumberyes–
earnednumberyes–
lowersstringyes–
raisesstringyes–
remainingnumberyes–
saysstringyes–
usednumberyes–

No examples provided.

brydge_report_outcome ~138

Tell BRYDGE what you believe happened after you carried out an allowed action. BRYDGE keeps your report beside what it finds in the destination's records; the report never changes the finding.

NameTypeReqDescription
authorizationstringyesThe authorization id brydge_supervise returned for the action.
outcomestringyesSUCCEEDED: it was carried out and did what it was meant to. FAILED: the destination refused it or errored. REVERSED: it happened and was undone. CORRECTED: it happened and had to be fixed afterwards.
saidstring–What the destination said, in its own words.
NameTypeReqDescription
authorizationstringyes–
recordedstringyes–

No examples provided.

brydge_supervise ~253

Ask BRYDGE whether you may take an action, before you take it. ALLOWED returns an authorization id: carry the action out and write that id into the record it creates, where the destination keeps it (for a Stripe refund: metadata.brydge_authorization). ESCALATED means a person decides: do not carry it out, and once they have answered, ask again with the same idempotency_key and details to get their answer.

NameTypeReqDescription
actionstringyesThe kind of work, as it is set up in BRYDGE, such as refund.
factsobject–What BRYDGE's rules judge the action by, such as {"amount": 4200}. BRYDGE compares a fact named amount with the amount in the destination's record, so give it in the same units.
idempotency_keystringyesA name for this one intended action, such as refund:ch_123. Send the same value whenever you ask about the same action again, on a retry or once a person has answered; never reuse it for a different…
targetstringyesWhat the work acts on: the charge, order or ticket id.
NameTypeReqDescription
authorizationstringyes–
becausestringyes–
decisionstringyes–
replayedbooleanyes–
settled–yes–
unobservedarrayyes–

No examples provided.

brydge_verify ~122

Check whether an action actually happened. BRYDGE reads the destination system's own records now, with its own credential, and compares them with what it permitted. Only VERIFIED means it happened as permitted; FAILED, MISMATCH, UNKNOWN (BRYDGE could not tell) and PENDING (still in progress) are not. Use it before you tell anyone the work is done. A check that finds something new is billed; asking again when nothing has changed is free.

NameTypeReqDescription
authorizationstringyesThe authorization id brydge_supervise returned for the action.
NameTypeReqDescription
agentAgreedboolean|nullyes–
authorizationstringyes–
becausestringyes–
checkedAtstring|nullyes–
claimedstring|nullyes–
externalRefstring|nullyes–
reasonstring|nullyes–
replayedbooleanyes–
statestringyes–

No examples provided.

Install

How do I install the BRYDGE MCP server?

BRYDGE runs locally as an npm package, launched with npx -y brydge-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 · brydge-mcp

# add to Claude Code
claude mcp add com-brydge-ai-brydge -- npx -y brydge-mcp
Common questions

What is the BRYDGE MCP server?

BRYDGE is an MCP server listed in the public MCP registry as com.brydge-ai/brydge. Checks whether an agent's actions actually happened, against the destination's own records. This page covers its npm package (brydge-mcp).

Is the BRYDGE MCP server safe to use?

BRYDGE scores 84 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 BRYDGE MCP server expose?

BRYDGE exposes 5 tools: brydge_supervise, brydge_report_outcome, brydge_verify, brydge_get_finding, brydge_get_headroom. Their descriptions and schemas cost roughly 665 tokens of context every time the server is loaded.

Is the BRYDGE MCP server still maintained?

BRYDGE 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 BRYDGE MCP server under?

BRYDGE 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 BRYDGE MCP server?

VerifyMCP ran 16 checks on BRYDGE, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. 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.