Skip to content

eDiscovery Decoder News/Calc MCP server

com.ediscoverydecoder/mcpediscoverydecoder.comstreamable-httpv0.1.0Scanned

Free educational MCP for read-only eDiscovery news and TAR/review calculators.

15 tools: 6 change things and 9 only read.

Tools: 0 delete, 0 irreversible, 6 write, 9 read.
  • Reads private data · 1
  • Reads text others write · 3
  • Can send data out · 1
  • 1 finding

Sign-in required, no OAuth metadata. Remote posture

With Anlyon

6 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the eDiscovery Decoder News/Calc MCP server can do

The eDiscovery Decoder News/Calc MCP server is published by ediscoverydecoder.com, a domain the MCP Registry verified. It has 15 tools. It can create or change data (6 tools: calculate_review_metrics, calculate_elusion, calculate_sample_size, calculate_tar_recall_estimate and 2 more), but cannot delete data. 9 tools only read.

1 tool reads private data (compare_tar_cutoffs); 3 tools bring in text other people can write (get_resource_content, search_news and get_news_brief); 1 tool can send data out of your system (get_resource_content). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.

Its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 13, 2026, version 0.1.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

15 tools

Changes things 6Claude Code: ask
  • calculate_control_set_recallCalculate recall against a known control set: the share of documents already confirmed relevant that the workflow found, with a Wilson confidence interval.1 finding

    Why it is in this group

    • The name "calculate_control_set_recall" says "set": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "calculate_control_set_recall" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "calculate_control_set_recall" says "set": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Calculate recall against a known control set: the share of documents already confirmed relevant that the workflow found, with a Wilson confidence interval. Use when you have relevant-found and relevant-missed counts from a fixed reference set. For recall from a confusion matrix use calculate_review_metrics; from a discard-set sample use calculate_tar_recall_estimate. Aggregate counts only; not legal advice.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • calculate_elusionEstimate how much responsive/relevant material may remain in a set you chose NOT to review (the discard, null, or 'elusion' set).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Estimate how much responsive/relevant material may remain in a set you chose NOT to review (the discard, null, or 'elusion' set). Use when a random sample of that excluded set has been coded — e.g. 'we sampled 400 culled docs and found 2 relevant.' Returns the elusion rate and a Wilson confidence interval. For an overall recall % from the same sample, use calculate_tar_recall_estimate. Aggregate counts only; not legal advice.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • calculate_prevalence_richnessEstimate how rich or prevalent a population is — the share that is responsive/relevant/positive — from positive hits in a random sample, with a Wilson confidence interval.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Estimate how rich or prevalent a population is — the share that is responsive/relevant/positive — from positive hits in a random sample, with a Wilson confidence interval. Use for 'what % of this set is relevant?' or to size review scope and cost expectations. Aggregate counts only; not legal advice.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • calculate_review_metricsScore a coded sample when you have a full confusion matrix (true/false positives and negatives) — e.g.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Score a coded sample when you have a full confusion matrix (true/false positives and negatives) — e.g. comparing a TAR model's calls against a reviewer's. Returns recall, precision, F1, accuracy, and in-sample elusion. Use calculate_control_set_recall if you only have relevant-found vs relevant-missed; calculate_elusion for a discard/null-set sample. Aggregate counts only; not legal advice.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • calculate_sample_sizeWork out how many documents to randomly sample to estimate a proportion (e.g.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Work out how many documents to randomly sample to estimate a proportion (e.g. richness or elusion) at a target confidence level and margin of error, with finite-population correction. Use when planning a sample before review — 'how big a sample do we need?' Aggregate inputs only; not legal advice.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • calculate_tar_recall_estimateEstimate overall TAR recall and how many responsive docs were missed, by combining the responsive count already found with an elusion sample of the excluded set.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Estimate overall TAR recall and how many responsive docs were missed, by combining the responsive count already found with an elusion sample of the excluded set. Use when the user wants a recall % for the whole workflow, not just the elusion rate. For only the elusion rate and its interval, use calculate_elusion. Aggregate counts only; not legal advice.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 9Show 9 read-only tools
  • compare_tar_cutoffsCompare candidate TAR score or rank cutoffs side by side: for each cutoff, how many docs sit above it, its share of the scored set, and (if responsive counts are given) an estimate…Reads private dataNo findings

    Why it is in this group

    • The name "compare_tar_cutoffs" says "compare": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "compare" and "doc": it reads documents.
    Description, as the server wrote it
    Compare candidate TAR score or rank cutoffs side by side: for each cutoff, how many docs sit above it, its share of the scored set, and (if responsive counts are given) an estimated precision. Use when deciding where to draw the review/cull line. Aggregate counts only; not legal advice.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_demo_guideReturn a short, human-readable walkthrough for testing this server: the endpoint, the tool/prompt/resource names, and ready-to-paste sample prompts.No findings

    Why it is in this group

    • The name "get_demo_guide" says "get": a word for reading.
    Description, as the server wrote it
    Return a short, human-readable walkthrough for testing this server: the endpoint, the tool/prompt/resource names, and ready-to-paste sample prompts. Use to give someone a guided demo. For the full machine-readable capability catalog, use list_capabilities instead.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_news_briefGet the current eDiscovery Decoder news brief: top stories plus a Week in Review breakdown, returned both as structured data and as display-ready Markdown (formatted_brief) with a …Reads text others writeNo findings

    Why it is in this group

    • The name "get_news_brief" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "get" and "review": it reads comments, which other people can write.
    Description, as the server wrote it
    Get the current eDiscovery Decoder news brief: top stories plus a Week in Review breakdown, returned both as structured data and as display-ready Markdown (formatted_brief) with a 'why it matters' line per story. Use when the user wants a roundup or summary of current eDiscovery AI news rather than a keyword search.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_prompt_templateReturn the rendered text of one of this server's guided prompts (mcp-demo-tour, tar-matter-kickoff, weekly-digest).No findings

    Why it is in this group

    • The name "get_prompt_template" says "get": a word for reading.
    Description, as the server wrote it
    Return the rendered text of one of this server's guided prompts (mcp-demo-tour, tar-matter-kickoff, weekly-digest). Use when the client can call tools but cannot open MCP prompts directly, or when you want to inspect a prompt's wording before using it.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_resource_contentFetch the JSON behind a supported edd:// resource — the demo guide, TAR learning path, glossary, or news (latest / brief / by-date).Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "get_resource_content" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe input takes a URL (input.uri), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.uri): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Fetch the JSON behind a supported edd:// resource — the demo guide, TAR learning path, glossary, or news (latest / brief / by-date). Use when you want resource content but the client cannot read MCP resources directly, e.g. to pull glossary definitions or the news brief as a normal tool result.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_capabilitiesList the full eDiscovery Decoder MCP surface — every tool, prompt, and resource, plus the suggested demo flow and safety boundaries — with an example prompt for each.No findings

    Why it is in this group

    • The name "list_capabilities" says "list": a word for reading.
    Description, as the server wrote it
    List the full eDiscovery Decoder MCP surface — every tool, prompt, and resource, plus the suggested demo flow and safety boundaries — with an example prompt for each. Call this first when you are unsure which tool fits the user's question, or when tool-search shows only a partial list.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • pingHealth check: confirm the eDiscovery Decoder News/Calc MCP server is reachable before a demo or when troubleshooting a connection.No findings

    Why it is in this group

    • The name "ping" says "ping": a word for reading.
    Description, as the server wrote it
    Health check: confirm the eDiscovery Decoder News/Calc MCP server is reachable before a demo or when troubleshooting a connection. Returns server name and version. No inputs.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • search_newsFind recent eDiscovery / legal-AI / TAR news by topic, tag, or date range.Reads text others writeNo findings

    Why it is in this group

    • The name "search_news" says "search": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Find recent eDiscovery / legal-AI / TAR news by topic, tag, or date range. Use when the user asks what's new or recent in eDiscovery, wants stories on a subject, or asks about a time window. For a ready-made top-stories roundup instead, use get_news_brief.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • validate_sample_designQC a TAR validation sampling plan: check whether it has the documented elements needed for a defensibility discussion (population, sample size, confidence level, sampling frame/met…No findings

    Why it is in this group

    • The name "validate_sample_design" says "validate": a word for reading.
    Description, as the server wrote it
    QC a TAR validation sampling plan: check whether it has the documented elements needed for a defensibility discussion (population, sample size, confidence level, sampling frame/method, randomization, etc.) and flag what is missing or inconsistent. Use to sanity-check a sampling protocol before relying on it. Reviews metadata only — not a legal sufficiency opinion.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

3 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write3
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__ediscoverydecoder__get_resource_content"
    ]
  }
}

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Sign-in required, no OAuth metadata

Looked at Nov 20, 2026, 18:37 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
402
tools/list served without credentials
no
Tools that change things, listed without credentials
0
Protocol version
not observed
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed

The probe stopped: initialize answered HTTP 402.

Posture changes

  1. Nov 20, 2026
    • HTTP status of an anonymous initialize: 200 to 402
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 6 to 0
    • Protocol version: 2025-06-18 to none

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "calculate_control_set_recall" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "calculate_control_set_recall" says "set": a word for a change.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 402; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 6 -> 0 (and 1 more).View diff
    • HTTP status of an anonymous initialize: 200 to 402
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 6 to 0
    • Protocol version: 2025-06-18 to none
  2. Tools12 changed.~12 changedView diff

Install

Pinned to version 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http ediscoverydecoder https://mcp.ediscoverydecoder.com/mcp
claude mcp add --transport http ediscoverydecoder https://mcp.ediscoverydecoder.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__ediscoverydecoder__ping",
      "mcp__ediscoverydecoder__list_capabilities",
      "mcp__ediscoverydecoder__get_demo_guide",
      "mcp__ediscoverydecoder__get_prompt_template",
      "mcp__ediscoverydecoder__search_news",
      "mcp__ediscoverydecoder__get_news_brief",
      "mcp__ediscoverydecoder__compare_tar_cutoffs",
      "mcp__ediscoverydecoder__validate_sample_design"
    ],
    "ask": [
      "mcp__ediscoverydecoder__get_resource_content",
      "mcp__ediscoverydecoder__calculate_review_metrics",
      "mcp__ediscoverydecoder__calculate_elusion",
      "mcp__ediscoverydecoder__calculate_sample_size",
      "mcp__ediscoverydecoder__calculate_tar_recall_estimate",
      "mcp__ediscoverydecoder__calculate_prevalence_richness",
      "mcp__ediscoverydecoder__calculate_control_set_recall"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as ediscoverydecoder. Review it before you use it.

Capability tags behind 4 rules
  • mcp__ediscoverydecoder__get_resource_content untrusted-input, outbound
  • mcp__ediscoverydecoder__search_news untrusted-input
  • mcp__ediscoverydecoder__get_news_brief untrusted-input
  • mcp__ediscoverydecoder__compare_tar_cutoffs private-data

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/com.ediscoverydecoder/mcp/verify?hash=951a2b76308041dcca2ae433202570c5098b2d6a20de11466535362ac48b28da" | jq -e '.changed == false'

Pinned hash 951a2b763080, from Nov 13, 2026, 03:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.ediscoverydecoder/mcp/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.ediscoverydecoder/mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/com.ediscoverydecoder/mcp.svg)](https://radar.anlyon.com/servers/com.ediscoverydecoder/mcp)

Source: MCP Registry. Synced Oct 21, 2026, 17:54 UTC.

eDiscovery Decoder News/Calc MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the eDiscovery Decoder News/Calc MCP server safe?

No scan can promise that. What its definitions show: 15 tools, 6 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the eDiscovery Decoder News/Calc MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the eDiscovery Decoder News/Calc MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the eDiscovery Decoder News/Calc MCP server have?

15 tools: 6 write, 9 read. calculate_review_metrics, calculate_elusion, calculate_sample_size, calculate_tar_recall_estimate, calculate_prevalence_richness, calculate_control_set_recall, ping, list_capabilities and 7 more.

Does the eDiscovery Decoder News/Calc MCP server need sign-in or OAuth?

Its remote endpoint did not answer the last anonymous look.

Does the eDiscovery Decoder News/Calc MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): get_resource_content.

Has the eDiscovery Decoder News/Calc MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 13, 2026. Every change is on this page and in its Atom feed.