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.

PromptSpeak Governance

NPM · @CHRBAILEY/PROMPTSPEAK-MCP-SERVER · SCANNED SEP 25

Pre-execution governance for AI agents. Validates tool calls before they execute.

0 this week 79 Trust /100
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 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
  • 53 of 133 dependencies flagged as unhealthy (2 deprecated). 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 (MIT).Pass
  • Actively maintained (last published 157 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability67
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 3522 tokens (~62/item across 56 items; 56 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management87
  • Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage89
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 68% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 5 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "ps_execute" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 56 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
Install

How do I install the PromptSpeak Governance MCP server?

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

npm · @chrbailey/promptspeak-mcp-server

# add to Claude Code
claude mcp add chrbailey-promptspeak -- npx -y @chrbailey/promptspeak-mcp-server
// .cursor/mcp.json
{
  "mcpServers": {
    "chrbailey-promptspeak": {
      "command": "npx",
      "args": [
        "-y",
        "@chrbailey/promptspeak-mcp-server"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "chrbailey-promptspeak": {
      "command": "npx",
      "args": [
        "-y",
        "@chrbailey/promptspeak-mcp-server"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add chrbailey-promptspeak -- npx -y @chrbailey/promptspeak-mcp-server
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "chrbailey-promptspeak": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@chrbailey/promptspeak-mcp-server"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add chrbailey-promptspeak --command npx --arg -y --arg @chrbailey/promptspeak-mcp-server
# ~/.hermes/config.yaml
mcp_servers:
  chrbailey-promptspeak:
    command: "npx"
    args: ["-y", "@chrbailey/promptspeak-mcp-server"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "chrbailey-promptspeak": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@chrbailey/promptspeak-mcp-server"
      ]
    }
  }
}
# add to Vellum
assistant mcp add chrbailey-promptspeak -t stdio -c npx -a -y @chrbailey/promptspeak-mcp-server
// mcp.json
{
  "mcpServers": {
    "chrbailey-promptspeak": {
      "command": "npx",
      "args": [
        "-y",
        "@chrbailey/promptspeak-mcp-server"
      ]
    }
  }
}
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.

  • 25 Sept 26 +1
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 23 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 22 Sept 26 +1
    • Stability: 0.97 → pass security
  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 −2
    • Stability: pass → 0.80 functional
  • 15 Sept 26 0
    • Stability: 0.97 → pass security
  • 14 Sept 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.

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 25 Sept 2026 · Analysed npm/@chrbailey/promptspeak-mcp-server@0.4.1

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 133 packages
Packages resolved 133
Deprecated 2
Stale 52
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 56 exposed · ~3,522 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
ps_audit_get ~36

Get audit log entries.

NameTypeReqDescription
actionstring––
limitnumber––
sincenumber––

No output schema declared.

No examples provided.

ps_capability_get ~25

Report this server's PromptSpeak capabilities (version, verb count, namespaces).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

ps_confidence_bulk_set ~25

Set multiple confidence thresholds at once.

NameTypeReqDescription
thresholdsobjectyes–

No output schema declared.

No examples provided.

ps_confidence_get ~15

Get all confidence thresholds.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

ps_confidence_set ~37

Set a confidence threshold. This is the hidden knob for operators.

NameTypeReqDescription
thresholdstringyes–
valuenumberyes–

No output schema declared.

No examples provided.

ps_config_activate ~23

Activate a registered policy overlay.

NameTypeReqDescription
overlayIdstringyes–

No output schema declared.

No examples provided.

ps_config_export ~15

Export current configuration for backup.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

ps_config_get ~18

Get current configuration including active overlay and thresholds.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

ps_config_import ~29

Import configuration from backup.

NameTypeReqDescription
datastringyes–
expectedChecksumstring––

No output schema declared.

No examples provided.

ps_config_set ~30

Register a new policy overlay.

NameTypeReqDescription
overlayobjectyes–
overlayIdstringyes–

No output schema declared.

No examples provided.

ps_delegate ~75

Delegate a task from parent agent to child agent. Enforces inheritance rules and constraint propagation.

NameTypeReqDescription
childAgentIdstringyes–
childFramestringyes–
inheritanceModestring––
parentAgentIdstringyes–
parentFramestringyes–
taskobject––

No output schema declared.

No examples provided.

ps_delegate_list ~38

List delegations for an agent.

NameTypeReqDescription
agentIdstringyes–
rolestring––
statusstring––

No output schema declared.

No examples provided.

ps_delegate_revoke ~40

Revoke an active delegation.

NameTypeReqDescription
delegationIdstringyes–
parentAgentIdstringyes–
reasonstring––

No output schema declared.

No examples provided.

ps_execute ~74

Execute an action under PromptSpeak frame governance. The gatekeeper validates and enforces constraints.

NameTypeReqDescription
actionobjectyes–
agentIdstringyesUnique identifier for the executing agent
framestringyesThe governing PromptSpeak frame
parentFramestring–Parent frame if part of delegation chain

No output schema declared.

No examples provided.

ps_execute_batch ~125

Execute multiple actions under a single frame. Supports sequential or parallel execution with optional stop-on-failure.

NameTypeReqDescription
actionsarrayyesArray of actions to execute under the frame
agentIdstringyesUnique identifier for the executing agent
framestringyesThe governing PromptSpeak frame for all actions
parallelboolean–Execute all actions in parallel instead of sequentially
parentFramestring–Parent frame if part of delegation chain
stopOnFirstFailureboolean–Stop executing remaining actions on first failure (sequential only)

No output schema declared.

No examples provided.

ps_execute_dry_run ~56

Check if an action would succeed without executing. Returns decision and coverage analysis.

NameTypeReqDescription
actionobjectyes–
agentIdstringyes–
framestringyes–
parentFramestring––

No output schema declared.

No examples provided.

ps_expand ~39

Expand a PromptSpeak expression to natural English. Used by safety filters for human-readable action descriptions.

NameTypeReqDescription
expressionstringyesPromptSpeak expression to expand

No output schema declared.

No examples provided.

ps_feature_get ~14

Get all feature flags.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

ps_feature_set ~28

Set a feature flag.

NameTypeReqDescription
enabledbooleanyes–
flagstringyes–

No output schema declared.

No examples provided.

ps_handshake_initiate ~28

Start a PromptSpeak verification handshake. Returns probe expression to send to remote agent.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

ps_handshake_respond ~41

Handle an incoming PromptSpeak handshake probe. Parses, validates, and echoes confirmation.

NameTypeReqDescription
inputstringyesThe handshake probe expression to respond to

No output schema declared.

No examples provided.

ps_hold_approve ~102

Approve a held execution request. The operation will proceed with optional modifications.

NameTypeReqDescription
executeNowboolean–Execute immediately after approval (default: true)
holdIdstringyesThe hold ID to approve
modifiedArgsobject–Optional: Modified arguments to use instead of original
modifiedFramestring–Optional: Modified frame to use instead of original
reasonstring–Reason for approval (for audit trail)

No output schema declared.

No examples provided.

ps_hold_config ~53

Configure hold behavior and thresholds. Controls when operations are held for human review.

NameTypeReqDescription
actionstringyesGet current config or set new config
configobject–Configuration to set (only for action=set)

No output schema declared.

No examples provided.

ps_hold_list ~61

List all pending holds awaiting human approval. Returns holds for risky operations that were blocked pending review.

NameTypeReqDescription
agentIdstring–Optional: Filter holds by agent ID
includeExpiredboolean–Include expired holds in the list (default: false)

No output schema declared.

No examples provided.

ps_hold_reject ~69

Reject a held execution request. The operation will not proceed.

NameTypeReqDescription
haltAgentboolean–Also halt the agent that made the request (default: false)
holdIdstringyesThe hold ID to reject
reasonstring–Reason for rejection (for audit trail)

No output schema declared.

No examples provided.

ps_hold_stats ~34

Get hold statistics and history.

NameTypeReqDescription
historyLimitnumber–Number of historical decisions to return (default: 10)

No output schema declared.

No examples provided.

ps_parse ~58

Parse a PromptSpeak EBNF expression into an AST. Returns AST tree and metadata (verb count, pipes, branches).

NameTypeReqDescription
expressionstringyesPromptSpeak expression (e.g., "::analyze{document}[security]|format:json")

No output schema declared.

No examples provided.

ps_registry_audit ~36

Get full change history for a verb (registrations, transitions, updates).

NameTypeReqDescription
symbolstringyesVerb symbol to audit

No output schema declared.

No examples provided.

ps_registry_lookup ~37

Resolve a verb symbol to its full definition, including aliases.

NameTypeReqDescription
symbolstringyesVerb symbol (e.g., "::analyze")

No output schema declared.

No examples provided.

ps_registry_namespace ~40

List all verbs registered in a namespace.

NameTypeReqDescription
namespacestringyesNamespace to list (e.g., "ps:core", "ps:gov")

No output schema declared.

No examples provided.

ps_registry_propose ~86

Submit a new verb for review. Created with status: proposed.

NameTypeReqDescription
categorystring–Verb category
definitionstringyesSemantic definition of the verb
namespacestringyesNamespace (e.g., "ps:custom")
safety_classstring–Safety classification
symbolstringyesVerb symbol (e.g., "::myverb")

No output schema declared.

No examples provided.

ps_registry_status ~31

Check the lifecycle state and safety classification of a verb.

NameTypeReqDescription
symbolstringyesVerb symbol to check

No output schema declared.

No examples provided.

ps_registry_version ~21

Get current spec version, verb count, and registry statistics.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

ps_security_config ~75

Configure security detection patterns. List, enable, disable, or change severity of patterns.

NameTypeReqDescription
actionstringyesConfiguration action to perform
patternIdstring–Pattern ID to modify (required for enable, disable, set_severity)
severitystring–New severity level (required for set_severity)

No output schema declared.

No examples provided.

ps_security_gate ~69

Scan code and enforce security policy. Blocks on critical findings, holds high-severity for review, warns on medium, logs low/info.

NameTypeReqDescription
actionstringyesThe action being gated (e.g., "write_file", "edit_file")
contentstringyesCode content to scan

No output schema declared.

No examples provided.

ps_security_scan ~58

Scan code content for security vulnerabilities. Returns findings classified by severity (critical, high, medium, low, info).

NameTypeReqDescription
contentstringyesCode content to scan
patternsarray–Optional: Only run these specific pattern IDs

No output schema declared.

No examples provided.

ps_state_drift_history ~42

Get drift history for an agent.

NameTypeReqDescription
agentIdstringyes–
limitnumber––
sincenumber–Unix timestamp

No output schema declared.

No examples provided.

ps_state_get ~31

Get current state of an agent including drift metrics and circuit breaker status.

NameTypeReqDescription
agentIdstringyes–

No output schema declared.

No examples provided.

ps_state_halt ~35

Immediately halt an agent by opening its circuit breaker.

NameTypeReqDescription
agentIdstringyes–
reasonstringyes–

No output schema declared.

No examples provided.

ps_state_recalibrate ~60

Recalibrate agent drift baseline. Optionally provide a new baseline configuration.

NameTypeReqDescription
agentIdstringyesAgent to recalibrate
newBaselineobject–Optional new baseline configuration. If omitted, recalibrates from current state.

No output schema declared.

No examples provided.

ps_state_reset ~67

Reset agent state. Can reset circuit breaker, drift metrics, and/or baseline.

NameTypeReqDescription
agentIdstringyes–
reasonstringyes–
resetBaselineboolean––
resetCircuitBreakerboolean––
resetDriftMetricsboolean––

No output schema declared.

No examples provided.

ps_state_resume ~37

Resume a halted agent.

NameTypeReqDescription
agentIdstringyes–
reasonstringyes–
resetMetricsboolean––

No output schema declared.

No examples provided.

ps_state_system ~23

Get overall system state including all agents, operations, and drift alerts.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

ps_symbol_add_alternative ~172

Add an alternative explanation to a symbol's findings. CRITICAL for preventing false positives: When a pattern-based finding could have multiple explanations, document them here. Adding high-likelihood alternatives automatically reduces confidence in the original claim. Examples: - "9 identical payments" → Alternative: "Monthly insurance premium financing" - "Large round numbers" → Alternative: "Negotiated contract amounts" - "Vendor with single customer" → Alternative: "Subsidiary company"

NameTypeReqDescription
added_bystringyesWho is adding this alternative
alternativestringyesDescription of the alternative explanation
likelihoodnumberyesEstimated likelihood this alternative is correct (0-1)
reasoningstring–Why this alternative is plausible
symbolIdstringyesSymbol ID to update

No output schema declared.

No examples provided.

ps_symbol_create ~436

Create a new directive symbol in the registry. Symbol IDs follow the pattern: - Public companies: Ξ.{TICKER}.{PERIOD} (e.g., Ξ.NVDA.Q3FY25) - People: Ξ.I.{NAME}.{CONTEXT} (e.g., Ξ.I.JENSEN_HUANG.BIO) - Events: Ξ.E.{TYPE}.{ID} (e.g., Ξ.E.EARNINGS.NVDA.20241120) - Sectors: Ξ.S.{SECTOR}.{CONTEXT} (e.g., Ξ.S.SEMICONDUCTORS.2024) - Tasks: Ξ.T.{PROJECT}.{ID} (e.g., Ξ.T.PORTFOLIO_REVIEW.001) - Knowledge: Ξ.K.{DOMAIN}.{TOPIC} (e.g., Ξ.K.CHEMISTRY.WATER) - Queries: Ξ.Q.{DATASET}.{ID} (e.g., Ξ.Q.DEEPSEARCHQA.001)

NameTypeReqDescription
anti_requirementsarray–MUST NOT include these elements
categorystring–Category (auto-inferred from ID if not provided)
commanders_intentstringyesUltimate goal in one sentence - the north star
created_bystring–Creator identifier
howobjectyes–
key_termsarray–Terms that MUST appear in output
parent_symbolstring–Parent symbol ID for hierarchical symbols
related_symbolsarray–Related symbol IDs
requirementsarrayyesMUST include these elements
symbolIdstringyesUnique symbol ID following namespace rules (e.g., Ξ.NVDA.Q3FY25)
tagsarray–Freeform tags for filtering
whatstringyesWhat is being analyzed or done
whenstringyesTime context
wherestringyesScope (company, market, geography)
whostringyesWho needs this / who is the audience
whystringyesWhy this matters / purpose

No output schema declared.

No examples provided.

ps_symbol_delete ~38

Delete a symbol from the registry.

NameTypeReqDescription
reasonstringyesReason for deletion
symbolIdstringyesSymbol ID to delete

No output schema declared.

No examples provided.

ps_symbol_format ~49

Format a symbol for inclusion in a prompt. Returns LLM-ready text.

NameTypeReqDescription
formatstring–Format style (default: full)
symbolIdstringyesSymbol ID to format

No output schema declared.

No examples provided.

ps_symbol_get ~84

Retrieve a directive symbol by ID. Returns the full symbol with all grounding context.

NameTypeReqDescription
include_changelogboolean–Include version changelog (default: true)
symbolIdstringyesSymbol ID to retrieve (e.g., Ξ.NVDA.Q3FY25)
versionnumber–Specific version to retrieve (optional, defaults to latest)

No output schema declared.

No examples provided.

ps_symbol_import ~114

Bulk import symbols from external data (HuggingFace, JSON, etc.).

NameTypeReqDescription
categorystringyesCategory for imported symbols
data–yesThe data to import (format depends on source)
defaultsobject–Default values for fields not in source data
id_prefixstringyesPrefix for generated symbol IDs (e.g., Ξ.Q.DEEPSEARCHQA)
sourcestringyesData source format
transformobject–Field mapping from source data to symbol fields

No output schema declared.

No examples provided.

ps_symbol_list ~107

List symbols with optional filtering.

NameTypeReqDescription
categorystring–Filter by category
created_afterstring–Filter by creation date (ISO 8601)
created_beforestring–Filter by creation date (ISO 8601)
limitnumber–Max results (default: 50)
offsetnumber–Pagination offset
searchstring–Search in symbolId and commanders_intent
tagsarray–Filter by tags

No output schema declared.

No examples provided.

Common questions

What is the PromptSpeak Governance MCP server?

PromptSpeak Governance is an MCP server listed in the public MCP registry as io.github.chrbailey/promptspeak. Pre-execution governance for AI agents. Validates tool calls before they execute. This page covers its npm package (@chrbailey/promptspeak-mcp-server).

Is the PromptSpeak Governance MCP server safe to use?

PromptSpeak Governance scores 79 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 25 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 PromptSpeak Governance MCP server expose?

PromptSpeak Governance exposes 56 tools: ps_validate, ps_validate_batch, ps_execute, ps_execute_dry_run, ps_execute_batch, and 51 more. Their descriptions and schemas cost roughly 3,522 tokens of context every time the server is loaded.

Is the PromptSpeak Governance MCP server still maintained?

PromptSpeak Governance is still listed as active in the MCP registry. We last reached this channel on 25 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 PromptSpeak Governance MCP server under?

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