ai.plith/plith
REMOTE · PLITH.AI
AI agent infrastructure: dedup, cost prediction, validation, governance, failure intelligence.
Available components
Last scanned (21 hours ago)
Scores higher than 59% of remote servers
Reachable. Last reached 21 Nov 2026.
Category AI and Machine Learning
Deprecated
This server is marked deprecated in the MCP registry.
The registry records this reason: Replaced by ai.plith/rigor at https://plith.ai/api/mcp/rigor.
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security80
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability73
- 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 1783 tokens (~297/item across 6 items; 4 tools + 2 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 Management13
- Stability check failed: schema churn in the 30 days we've observed: 11 tool removals, 4 breaking changes, 0 auth/transport breaks, 0 additions. See how to fix → Fail
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
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
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.
- 13 Nov 26 −7
- A breaking change shipped without a version bump: still 1.0.0 ▼ security
- Tool “burnrate_budget” was removed ▼ security
- Tool “burnrate_estimate” was removed ▼ security
- Tool “burnrate_optimize” was removed ▼ security
- Tool “burnrate_track” was removed ▼ security
- Tool “dedupq_check” was removed ▼ security
- Tool “dedupq_complete” was removed ▼ security
- Tool “guardrail_check” was removed ▼ security
- Tool “guardrail_create_policy” was removed ▼ security
- Tool “pitfalldb_query” was removed ▼ security
- Tool “pitfalldb_report” was removed ▼ security
- Tool “qualitygate_validate” was removed ▼ security
- Schema quality: 150 → 297 ▼ functional
- Prompt “agent-preflight” was removed ▼ functional
- Prompt “cost-aware-execution” was removed ▼ functional
- Prompt “output-validation” was removed ▼ functional
- Prompt “setup-guardrails” was removed ▼ functional
- Resource “GuardRail Policy Examples” was removed ▼ functional
- Resource “Operations Quickstart” was removed ▼ functional
- Resource “QualityGate Rule Examples” was removed ▼ functional
- Resource “Sample Failure Patterns” was removed ▼ functional
- Schema quality: excellent → good functional
- “rigor_execute” added an optional parameter “agent_id” cosmetic
- “rigor_execute” added an optional parameter “language” cosmetic
- “rigor_execute” added an optional parameter “mode” cosmetic
- “rigor_execute” added an optional parameter “refresh_connections” cosmetic
- “rigor_execute” added an optional parameter “workflow_id” cosmetic
- “rigor_execute” added an optional parameter “workflow_ids” cosmetic
- “rigor_plan” added an optional parameter “agent_id” cosmetic
- “rigor_plan” added an optional parameter “context” cosmetic
- “rigor_plan” added an optional parameter “language” cosmetic
- “rigor_execute” reworded the description of “context” cosmetic
- “rigor_execute” reworded the description of “delivery” cosmetic
- “rigor_execute” reworded the description of “preferences” cosmetic
- “rigor_execute” reworded the description of “task_description” cosmetic
- “rigor_execute” reworded the description of “task_type” cosmetic
- “rigor_plan” reworded the description of “preferences” cosmetic
- “rigor_plan” reworded the description of “task_description” cosmetic
- “rigor_plan” reworded the description of “task_type” cosmetic
- “rigor_execute” made “task_description” optional cosmetic
- 6 Nov 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
- 5 Nov 26 −6
- Stability: pass → fail ▼ security
- A breaking change shipped without a version bump: still 1.0.0 ▼ security
- Tool “burnrate_budget” dropped its output schema ▼ functional
- Tool “burnrate_estimate” dropped its output schema ▼ functional
- Tool “burnrate_optimize” dropped its output schema ▼ functional
- Tool “burnrate_track” dropped its output schema ▼ functional
- Tool “dedupq_check” dropped its output schema ▼ functional
- Tool “dedupq_complete” dropped its output schema ▼ functional
- Tool “guardrail_check” dropped its output schema ▼ functional
- Tool “guardrail_create_policy” dropped its output schema ▼ functional
- Tool “pitfalldb_query” dropped its output schema ▼ functional
- Tool “pitfalldb_report” dropped its output schema ▼ functional
- Tool “qualitygate_validate” dropped its output schema ▼ functional
- Tool “rigor_execute” dropped its output schema ▼ functional
- Tool “rigor_plan” dropped its output schema ▼ functional
- Tool “rigor_status” dropped its output schema ▼ functional
- Tool “rigor_workflows” dropped its output schema ▼ functional
- MCP protocol version: 2024-11-05 → 2025-06-18 functional
- 11 Oct 26 0
- “rigor_execute” added an optional parameter “context_fields” cosmetic
- “rigor_execute” added an optional parameter “prior_workflow_id” cosmetic
- “rigor_plan” added an optional parameter “context_fields” cosmetic
- “rigor_plan” added an optional parameter “prior_workflow_id” cosmetic
4 cosmetic changes on this day. Switch on “Show cosmetic changes” to see them.
- 10 Oct 26 0
- “rigor_execute” reworded the description of “task_description” cosmetic
- “rigor_plan” reworded the description of “task_description” cosmetic
2 cosmetic changes on this day. Switch on “Show cosmetic changes” to see them.
- 28 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
- 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
- 7 Sept 26 0
- “rigor_execute” reworded the description of “task_type” cosmetic
- “rigor_plan” reworded the description of “task_type” cosmetic
2 cosmetic changes on this day. Switch on “Show cosmetic changes” to see them.
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 · Probed https://plith.ai/api/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=plith.ai | CN=YR1,O=Let's Encrypt,C=US | 14 Oct 2026 | 12 Jan 2027 | RSA 2048 | SHA256-RSA | 6cf967a16061eb02f4acd6fd686f232ea91 |
| SANs: plith.ai | ||||||
| CN=YR1,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | a20253f15f2691c05dc1ce13b9bcca4e |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of plith.ai. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | DS published | 1814 | 8 | Verified |
| plith.ai. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=63072000; includeSubDomains; preload |
| content-security-policy | default-src 'self'; script-src 'self' 'unsafe-inline' 'wasm-unsafe-eval' https://umami.peaklight.news; style-src 'self' 'unsafe-inline'; img-src 'self' data: https:; font-src 'self' data:; connect-src 'self' https://*.supabase.co wss://*.supabase.co https://api.stripe.com https://umami.peaklight.news; frame-ancestors 'none'; form-action 'self'; base-uri 'self' |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | camera=(), microphone=(), geolocation=() |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://plith.ai/api/mcp | Verified | 200 | |
| http (plaintext) | http://plith.ai/api/mcp | HTTPS enforced | 308 | https://plith.ai/api/mcp |
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 →
rigor_execute ~761
Execute a structured workflow end-to-end. Call rigor_plan first (free) to preview the step sequence and cost estimate before committing credits. Classifies the task, selects the optimal tool sequence, and executes each step with the right LLM model. Returns a complete deliverable — solution designs, competitive analyses, governance documents, and more. Supports SSE streaming for real-time progress, webhook callback, or polling. For atomic work — classification, scoring, ranking, entity extraction, query parsing — set preferences.execution to 'direct' and declare preferences.output_contract to get validated JSON records from a single call, routed to the cheapest model that holds the schema.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | – | Your own label for the calling agent, at most 200 characters. Recorded on the workflow and its cost rows; never used for routing or authorization. |
| context | object | – | Additional context for the workflow. Persisted with a plan, so an execute by workflow_id inherits it unless it sends its own. |
| context_fields | array | – | Optional, with prior_workflow_id: the fields to carry over. Pass ["full_step_results"] for every step output in full. |
| delivery | object | – | How you receive progress and the result. Over REST the default is sse; over MCP it is polling, because most MCP clients cannot read a stream. |
| language | string | – | BCP 47 language code for the deliverable (for example "fr", "ja", "pt-BR"). Overrides the organization default. |
| mode | string | – | "interactive" returns interactive_waiting and runs 1 step per POST /api/rigor/step; otherwise "full". |
| preferences | object | – | Optional workflow preferences. The same shape on plan and execute; a plan stores them, and an execute by workflow_id inherits them. |
| prior_workflow_id | string | – | Optional: the workflow_id (wr_…) of a finished workflow in your workspace to build on. Its results are passed to this run as context. It is charged as a new run at the normal quote. |
| refresh_connections | boolean | – | Refresh your MCP connection state before the run starts. Defaults to true; a failed refresh never blocks the run. |
| task_description | string | – | Natural language description of the task, at least 2 words and at most 4,000 characters (200,000 across it and context.additional_context when task_type is compose). Be specific: include what you wan… |
| task_type | string | – | Optional hint to bypass automatic classification. Passing it also removes the slowest classification tiers from the critical path, so send it whenever you know the shape. Multi-step deliverable types… |
| workflow_id | string | – | The workflow_id (wr_…) a plan call returned. Runs that stored plan without re-planning. Required when task_description is absent. |
| workflow_ids | array | – | Several planned workflow ids (from a multi-intent plan) to run without re-planning. |
No output schema declared.
No examples provided.
rigor_plan ~525
Before executing a complex task, get a structured workflow plan with per-step cost estimates. Classifies your task, selects the optimal framework sequence, and returns the full plan without executing anything. The response's allowed_modes tells you whether this plan is eligible for direct execution. Free — no credits charged.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | – | Your own label for the calling agent, at most 200 characters. Recorded on the workflow and its cost rows; never used for routing or authorization. |
| context | object | – | Additional context for the workflow. Persisted with a plan, so an execute by workflow_id inherits it unless it sends its own. |
| context_fields | array | – | Optional, with prior_workflow_id: the fields to carry over. Pass ["full_step_results"] for every step output in full. |
| language | string | – | BCP 47 language code for the deliverable (for example "fr", "ja", "pt-BR"). Overrides the organization default. |
| preferences | object | – | Optional workflow preferences. The same shape on plan and execute; a plan stores them, and an execute by workflow_id inherits them. |
| prior_workflow_id | string | – | Optional: the workflow_id (wr_…) of a finished workflow in your workspace to build on. Its results are passed to this run as context. It is charged as a new run at the normal quote. |
| task_description | string | yes | Natural language description of the task, at least 2 words and at most 4,000 characters (200,000 across it and context.additional_context when task_type is compose). Be specific: include what you wan… |
| task_type | string | – | Optional hint to bypass automatic classification. Passing it also removes the slowest classification tiers from the critical path, so send it whenever you know the shape. Multi-step deliverable types… |
No output schema declared.
No examples provided.
rigor_status ~66
Check the status of a running or completed Rigor workflow. Returns progress, step results, and the full deliverable when complete. Use after rigor_execute with polling delivery to retrieve results.
| Name | Type | Req | Description |
|---|---|---|---|
| workflow_id | string | yes | The workflow ID returned by rigor_execute (format: wr_xxx). |
No output schema declared.
No examples provided.
rigor_workflows ~364
List and search Rigor workflows for your organization, with filtering and pagination. Returns status, progress, capacity usage, and available actions per workflow. Use to monitor workflow state, understand concurrent limit usage, identify stuck or completed workflows, and — via q — find prior work on a subject before commissioning it again. Pair a q hit with rigor_status to read that workflow's deliverable.
| Name | Type | Req | Description |
|---|---|---|---|
| counts_toward_limit | string | – | Filter to workflows counting toward the concurrent limit |
| created_after | string | – | ISO timestamp — only workflows created after this time |
| created_before | string | – | ISO timestamp — only workflows created before this time |
| cursor | string | – | Pagination cursor (created_at timestamp from previous page) |
| folder_id | string | – | Filter by folder ID. Pass "unassigned" for workflows in no folder |
| limit | number | – | Page size (default 20, max 100) |
| q | string | – | Search the workflow title and task description. Every whitespace-separated term must appear in one or the other, as a case-insensitive substring — so "vector search postgres" matches a task described… |
| status | string | – | Filter by status (comma-separated). Valid values: executing, step_executing, completed, failed, halted, pending_approval, cancelled. E.g. "halted,failed,pending_approval" |
| task_type | string | – | Filter by classified task type |
No output schema declared.
No examples provided.
How do I install the ai.plith/plith MCP server?
ai.plith/plith is a hosted endpoint at https://plith.ai/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · plith.ai
claude mcp add --transport http ai-plith-plith 'https://plith.ai/api/mcp'
What is the ai.plith/plith MCP server?
ai.plith/plith is an MCP server listed in the public MCP registry as ai.plith/plith. AI agent infrastructure: dedup, cost prediction, validation, governance, failure intelligence. This page covers its hosted endpoint (https://plith.ai/api/mcp).
Is the ai.plith/plith MCP server safe to use?
ai.plith/plith scores 73 out of 100 on VerifyMCP. 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 ai.plith/plith MCP server expose?
ai.plith/plith exposes 4 tools: rigor_plan, rigor_execute, rigor_status, rigor_workflows. Their descriptions and schemas cost roughly 1,716 tokens of context every time the server is loaded.
Does the ai.plith/plith MCP server require authentication?
No. We connected to ai.plith/plith without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the ai.plith/plith MCP server still maintained?
ai.plith/plith is marked deprecated 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 did VerifyMCP test on the ai.plith/plith MCP server?
VerifyMCP ran 13 checks on ai.plith/plith, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.