io.github.phaedo-labs/phaedo-mcp
NPM · PHAEDO-MCP · SCANNED SEP 26
Carry your Phaedo cognitive fingerprint into any MCP client: inject, consult, escalate, sign.
Available components
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 Security98
- 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
- 31 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
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 (Apache-2.0).Pass
- Actively maintained (last published 5 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability75
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1169 tokens (~129/item across 9 items; 8 tools + 1 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 Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage70
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 9% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 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.
How do I install the io.github.phaedo-labs/phaedo-mcp server?
io.github.phaedo-labs/phaedo-mcp runs locally as an npm package, launched with npx -y phaedo-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 · phaedo-mcp
claude mcp add phaedo-labs-phaedo-mcp -- npx -y phaedo-mcp
{
"mcpServers": {
"phaedo-labs-phaedo-mcp": {
"command": "npx",
"args": [
"-y",
"phaedo-mcp"
]
}
}
} {
"servers": {
"phaedo-labs-phaedo-mcp": {
"command": "npx",
"args": [
"-y",
"phaedo-mcp"
]
}
}
} codex mcp add phaedo-labs-phaedo-mcp -- npx -y phaedo-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"phaedo-labs-phaedo-mcp": {
"type": "local",
"command": [
"npx",
"-y",
"phaedo-mcp"
],
"enabled": true
}
}
} openclaw mcp add phaedo-labs-phaedo-mcp --command npx --arg -y --arg phaedo-mcp
mcp_servers:
phaedo-labs-phaedo-mcp:
command: "npx"
args: ["-y", "phaedo-mcp"] {
"McpServers": {
"phaedo-labs-phaedo-mcp": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"phaedo-mcp"
]
}
}
} assistant mcp add phaedo-labs-phaedo-mcp -t stdio -c npx -a -y phaedo-mcp
{
"mcpServers": {
"phaedo-labs-phaedo-mcp": {
"command": "npx",
"args": [
"-y",
"phaedo-mcp"
]
}
}
} 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.
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 20 Sept 26 +29
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
- Tool safety: Tool safety not yet verified: we do not have a sandbox capture of the tool definitions this version of the package serves yet. security
- Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. security
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- Schema quality: unverified → 100 ▲ functional
- First check of Schema quality: fail functional
- First check of Destructive annotations: pass functional
- First check of Schema quality: fail functional
- First check of Tool coverage: 9 functional
- First check of Schema quality: good functional
- Capabilities: Protocol version not yet verified: we do not have a sandbox capture of the MCP handshake this version of the package performs yet. functional
- Tool coverage: Tool coverage not yet verified: we do not have a sandbox capture of the tool definitions this version of the package serves yet. functional
- Schema quality: Schema quality not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. functional
- Package version: 0.2.2 → 0.3.0 functional
- 26 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 11 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 7 Aug 26 0
- Known CVEs: partial → pass ▲ security
- Security disclosure: fail → pass ▲ functional
- Dependency health: partial → 0.85 functional
- 5 Aug 26 0
- CVE-2026-69207 no longer affects this package ▲ security
- Known CVEs: fail → partial ▲ security
- 4 Aug 26 0
- CVE-2026-69207 affects this package: medium ▼ security
- Known CVEs: partial → fail ▼ security
- 2 Aug 26 0
- Provenance: unverified → fail ▼ security
- Install scripts: unverified → pass ▲ security
- Known CVEs: unverified → partial ▲ security
- Malware scan: unverified → pass ▲ security
- License: unverified → pass ▲ functional
- Dependency health: unverified → partial ▲ functional
- Maintenance: unverified → pass ▲ functional
- Licence: Apache-2.0 functional
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 26 Sept 2026 · Analysed npm/phaedo-mcp@0.3.0
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 96 packages
| Packages resolved | 96 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
phaedo_check_authorization Check standing authorizations for an action ~190
Deterministic pre-flight: check whether one of the user's standing authorizations (§10.5) already decides this action — escalate, decline, or pre-approve — without running the full consultation. Returns authorization_matched plus the authorized signal and the rule that fired. If no rule matches, fall back to phaedo_consult or your own default.
| Name | Type | Req | Description |
|---|---|---|---|
| action_binding | object | – | Binds this consultation to the concrete call it describes. The action_descriptor is your ACCOUNT of the action; this is the action. Recorded on the audit receipt so a later mismatch is provable, show… |
| action_descriptor | object | – | – |
| agent_credential | string | – | – |
| agent_id | string | – | – |
| consultation_type | string | – | – |
No output schema declared.
No examples provided.
phaedo_consult Consult the Phaedo fingerprint at a decision point ~185
Ask how the user's cognitive pattern bears on a decision — without ingesting the fingerprint. Returns a signal (proceed | proceed_with_note | clarify | escalate | decline), a confidence, a short rationale_hint, and a deference_level (how strongly to weight it). Use at agent decision points.
| Name | Type | Req | Description |
|---|---|---|---|
| action_binding | object | – | Binds this consultation to the concrete call it describes. The action_descriptor is your ACCOUNT of the action; this is the action. Recorded on the audit receipt so a later mismatch is provable, show… |
| action_descriptor | object | – | – |
| agent_credential | string | – | – |
| agent_id | string | – | – |
| consultation_type | string | yes | – |
| context | object | – | – |
No output schema declared.
No examples provided.
phaedo_escalate Escalate a blocking decision to the subject in real time ~227
When you're acting autonomously for the user and hit a decision you shouldn't make alone, escalate it to them live instead of guessing. Runs the consultation and, only if the signal is blocking (escalate/clarify), wakes the user's phone for an approve/deny/modify. Returns a request_id immediately — then poll phaedo_escalation_status and DO NOT PROCEED until it resolves (if the user doesn't answer in time, hold). Use for consequential, hard-to-undo actions.
| Name | Type | Req | Description |
|---|---|---|---|
| action_binding | object | – | Binds this consultation to the concrete call it describes. The action_descriptor is your ACCOUNT of the action; this is the action. Recorded on the audit receipt so a later mismatch is provable, show… |
| action_descriptor | object | – | – |
| agent_credential | string | – | – |
| agent_id | string | – | – |
| consultation_type | string | – | – |
| context | object | – | – |
No output schema declared.
No examples provided.
phaedo_escalation_status Check whether the subject has decided an escalation ~100
Poll an escalation you opened with phaedo_escalate. Returns resolved + the decision (approve | deny | modify) once the user answers, pending while you should keep waiting, or expired once the window lapsed (then HOLD — do not proceed). A resolved decision is recorded automatically as the act-as-me outcome.
| Name | Type | Req | Description |
|---|---|---|---|
| expires_at | number | – | – |
| receipt_id | string | – | – |
| request_id | string | yes | – |
No output schema declared.
No examples provided.
phaedo_record_outcome Record what the subject decided about a consulted action ~122
After you consulted Phaedo and the USER decided what to do, record their outcome on the receipt: approved | rejected | modified | unknown. Record what the USER chose, NOT whether you proceeded. A rejected/modified outcome teaches Phaedo how the user wants delegated work handled (the act-as-me channel). Defaults to the most recent receipt; pass receipt_id to mark a specific one.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_credential | string | – | – |
| agent_id | string | – | – |
| outcome | string | yes | – |
| receipt_id | string | – | – |
No output schema declared.
No examples provided.
phaedo_request_injection Request a Phaedo fingerprint injection ~89
Returns the user's Phaedo cognitive-fingerprint projection as a system-prompt block to insert at the start of an AI session, so the assistant responds in the user's style. Call once at session start and prepend the returned `projection`.
| Name | Type | Req | Description |
|---|---|---|---|
| consumer_id | string | – | – |
| mode | string | – | – |
| requested_layers | array | – | – |
| session_context | object | – | – |
No output schema declared.
No examples provided.
phaedo_sign_mandate Ask the subject to sign a payment authorization (AP2 Intent Mandate) ~130
Request the subject's cryptographic signature on an AP2 Intent Mandate built from their standing authorizations — a credential a merchant or payments network can verify. Returns a request_id and the unsigned mandate immediately; then poll phaedo_sign_status with BOTH, and DO NOT treat the mandate as authorized until it returns signed. The subject signs on their phone (Face ID, key in the Secure Enclave); they may also decline. Use only when you need a verifiable payment credential — not for ordinary consultations.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | – | – |
| prompt_playback | string | – | – |
No output schema declared.
No examples provided.
phaedo_sign_status Check whether the subject has signed the mandate ~106
Poll a request from phaedo_sign_mandate. Pass the request_id AND the mandate that call returned. Returns signed + the mandate carrying the verified signature once the subject signs, refused if they declined, pending while you should keep waiting, or expired once the window lapsed. A signed result is verified against the subject's published signing key before it is returned.
| Name | Type | Req | Description |
|---|---|---|---|
| expires_at | number | – | – |
| mandate | object | yes | – |
| request_id | string | yes | – |
No output schema declared.
No examples provided.
What is the io.github.phaedo-labs/phaedo-mcp server?
io.github.phaedo-labs/phaedo-mcp is listed in the public MCP registry as io.github.phaedo-labs/phaedo-mcp. Carry your Phaedo cognitive fingerprint into any MCP client: inject, consult, escalate, sign. This page covers its npm package (phaedo-mcp).
Is the io.github.phaedo-labs/phaedo-mcp server safe to use?
io.github.phaedo-labs/phaedo-mcp scores 68 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 26 September 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 io.github.phaedo-labs/phaedo-mcp server expose?
io.github.phaedo-labs/phaedo-mcp exposes 8 tools: phaedo_request_injection, phaedo_consult, phaedo_check_authorization, phaedo_record_outcome, phaedo_escalate, and 3 more. Their descriptions and schemas cost roughly 1,149 tokens of context every time the server is loaded.
Is the io.github.phaedo-labs/phaedo-mcp server still maintained?
io.github.phaedo-labs/phaedo-mcp is still listed as active in the MCP registry. We last reached this channel on 26 September 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 io.github.phaedo-labs/phaedo-mcp server under?
io.github.phaedo-labs/phaedo-mcp declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.