# CounselorAI (remote · api.counselorai.app)

College-access writing and financial-aid analysis tools for counselors, students, and families.

- Trust score: 84/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- remote · `api.counselorai.app`: 84/100 (this document), [markdown](https://verifymcp.io/servers/the-825-counselorai/api.md), [page](https://verifymcp.io/servers/the-825-counselorai/api)

## Channel facts

- Endpoint: `https://api.counselorai.app/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.2.0`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-21.

- **Endpoint Security**: 89/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 65/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2463 tokens (~189/item across 13 items; 13 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 63/100
  - Stability observed for 19 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 97/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 91% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the CounselorAI MCP server?

CounselorAI is a hosted endpoint at https://api.counselorai.app/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.

### Claude

```bash
claude mcp add --transport http the-825-counselorai 'https://api.counselorai.app/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "the-825-counselorai": {
      "url": "https://api.counselorai.app/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "the-825-counselorai": {
      "type": "http",
      "url": "https://api.counselorai.app/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.the-825-counselorai]
url = "https://api.counselorai.app/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "the-825-counselorai": {
      "type": "remote",
      "url": "https://api.counselorai.app/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add the-825-counselorai --url 'https://api.counselorai.app/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  the-825-counselorai:
    url: "https://api.counselorai.app/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "the-825-counselorai": {
      "Transport": "http",
      "Url": "https://api.counselorai.app/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add the-825-counselorai -t streamable-http -u 'https://api.counselorai.app/mcp'
```

### Other

```json
{
  "mcpServers": {
    "the-825-counselorai": {
      "type": "http",
      "url": "https://api.counselorai.app/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-21 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-19 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-16 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 81, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-09-14 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-12 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-10 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-08 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (13)

### `appeal` (~394 tokens)

Financial aid appeal letter

Draft a financial aid appeal letter to a college financial aid office. Call this when a family needs to ask for a review of an award: income dropped, an expense appeared, another school offered more, or the FAFSA was wrong. Returns the letter, not advice on whether to appeal. Runs a 5-step drafting pipeline, so it is the most expensive tool here and the slowest, typically 30 to 60 seconds.

Cost: about 353 credits (~$0.353) per call.

Input parameters:

- `amountNeeded` (string): The gap being asked for.
- `appealType` (string): What the appeal rests on. changed_circumstances is income loss or a new expense since the FAFSA, competing_offer is a match request, special_circumstances asks for a Professional Judgment review, err…
- `competing` (string): A competing offer to cite, if there is one.
- `counselorName` (string): Who the letter is from. The counselor stays the author; this tool drafts, it does not sign.
- `currentAward` (string): What the school offered, as written on the award letter.
- `keyDetails` (string, required): The circumstances, in the counselor or family's own words. This is what the letter is built out of, so specifics beat summaries.
- `length` (string): Roughly 330, 440 or 560 words.
- `naturalness` (integer): How plainly the letter should read. 1 is formal institutional, 5 is conversational.
- `schoolName` (string): The institution the appeal goes to.
- `status` (array): Student circumstances the letter should carry without labeling them. homeless and housing_insecure are the same category.
- `studentName` (string): The student this is about. Used in the output text.

### `rec` (~348 tokens)

Letter of recommendation

Draft a letter of recommendation from counselor notes. Call this to WRITE a letter. To critique one that already exists, call letterlens instead, which is much cheaper. Runs the same 5-step pipeline as appeal.

Cost: about 369 credits (~$0.369) per call.

Input parameters:

- `contribution` (string): What the student adds to a campus.
- `counselorName` (string): Who the letter is from. The counselor stays the author; this tool drafts, it does not sign.
- `major` (string)
- `profType` (string): Only when purpose is professional: which professional school, since each reads for different things.
- `purpose` (string): What the letter is for. undergraduate, graduate, internship and other are legacy aliases kept working for existing integrations.
- `recipient` (string): Who receives it, if named.
- `relationship` (string): How the counselor knows the student, and for how long.
- `resumeText` (string): Resume or activity list as plain text.
- `sampleText` (string): A sample of the counselor's own writing, so the letter lands in their voice rather than a generic one.
- `schools` (string): Target school or program.
- `selectivity` (string): How selective the target is. Shifts how much evidence the letter has to carry.
- `story` (string): A specific moment worth telling. The single highest-value field here.
- `studentName` (string): The student this is about. Used in the output text.
- `traits` (string, required): Three standout traits. Send prose, not a list of adjectives: the pipeline turns each one into a scene and needs something to work from.

### `letterlens` (~134 tokens)

Review a letter

Analyze a finished recommendation letter and return specific fixes: what is vague, what is asserted without evidence, what reads as generated. Read-only and far cheaper than drafting. Use it to critique a draft, not to rewrite one, and use revision to apply the fixes.

Cost: about 93 credits (~$0.093) per call.

Input parameters:

- `focus` (string): A specific thing to look hardest at, if there is one.
- `letterText` (string, required): The letter to review, as plain text.
- `purpose` (string): What the letter is for. A scholarship letter is read differently from a transfer letter.

### `awardlens` (~203 tokens)

Read an award letter

Break down one to three financial aid award letters: what is grant, what is loan, what is work-study that has to be earned, what the supported net price is, and what renewal conditions are buried in the language. Identifies missing facts and questions for the aid office. With more than one letter it compares them side by side. Read-only.

Cost: about 173 credits (~$0.173) per call.

Input parameters:

- `letter1` (string, required): First award letter, pasted as plain text.
- `letter2` (string): Second award letter, to compare against the first.
- `letter3` (string): Third award letter.
- `scorecardData` (array): Optional College Scorecard lines to ground the comparison: acceptance rate, graduation rate, average net price. Include the original Letter number and school/campus; unverified caller-supplied contex…
- `studentName` (string): The student this is about. Used in the output text.

### `fafsa` (~243 tokens)

FAFSA checklist

Produce a FAFSA action checklist for one student, keyed to their grade, dependency status and income band. Answers the process question a family actually has: what do we do, in what order, by when. Does not compute an award.

Cost: about 87 credits (~$0.087) per call.

Input parameters:

- `dependency` (string): Dependency drives whose income is reported. unsure is a valid answer and changes the checklist.
- `grade` (string): How far out the family is. 12 means act now.
- `income` (string): Household income band. Drives whether Pell is in play.
- `notes` (string): Anything else that should shape the output.
- `schools` (string): Schools on the list, if known. Deadlines differ by school.
- `specials` (array): Situations that change the filing rules: divorced or separated parents, a stepparent, a sibling also in college, undocumented status, foster care, housing instability, disability, a mid-year income c…
- `studentName` (string): The student this is about. Used in the output text.
- `timeline` (string): Where they are in the cycle.

### `aid` (~197 tokens)

Aid estimate explainer

Explain what a family is likely to see across a list of schools and why, in plain language. An explanation for a counselor to walk a family through, never an official determination, and the output says so.

Cost: about 73 credits (~$0.073) per call.

Input parameters:

- `context` (string): Household situation that affects the estimate.
- `fafsaContext` (string): What is already known from the FAFSA, including the SAI if it has come back.
- `income` (string): Household income, as the family stated it.
- `repayContext` (string): What the family has said about borrowing and what they can carry.
- `schoolCount` (integer): How many schools are being compared.
- `schoolSummaries` (string): One line per school: name, cost of attendance, anything already known about the offer.
- `studentName` (string): The student this is about. Used in the output text.

### `scholarship` (~202 tokens)

Scholarship matching

Surface scholarships worth this student's time and the angle their application should take for each. Runs a live web search, so it is slower and costs more than the other analysis tools, and the output carries a verification warning because scholarship programs change year to year. Treat the result as a research starting point.

Cost: about 165 credits (~$0.165) per call.

Input parameters:

- `activities` (string): Extracurriculars and leadership.
- `backgrounds` (array): Eligibility categories that unlock specific award pools.
- `gpa` (string)
- `grade` (string): Grade level or transfer status.
- `major` (string): Intended field. Departmental awards are usually the least contested.
- `notes` (string): Anything else that should shape the output.
- `state` (string): State of residence. State and regional awards have far smaller applicant pools than national ones.
- `studentName` (string): The student this is about. Used in the output text.

### `profile` (~208 tokens)

Student profile summary

Turn raw counselor notes into a structured student profile. Run this first when working one student across several tools: it is cheap, and its output is good input for the relationship, traits and story fields on rec, or keyDetails on appeal.

Cost: about 87 credits (~$0.087) per call.

Input parameters:

- `academics` (string): Coursework, GPA, testing, academic trajectory.
- `activities` (string)
- `challenges` (string): What the student has had to work around.
- `goals` (string)
- `grade` (string)
- `major` (string)
- `notes` (string): Anything else that should shape the output.
- `school` (string)
- `strengths` (string): What the counselor has actually observed, not adjectives.
- `studentName` (string): The student this is about. Used in the output text.
- `tags` (array): Background categories. Same vocabulary the scholarship tool uses, so a profile feeds straight into it.

### `revision` (~95 tokens)

Revise a draft

Apply one instruction to an existing letter and return the revised text. Pair it with letterlens: review to find the problems, revise to fix them. Changes only what the instruction asks for.

Cost: about 97 credits (~$0.097) per call.

Input parameters:

- `currentText` (string, required): The letter as it stands.
- `instruction` (string, required): What to change. One instruction per call gets a cleaner result than a list.

### `translate` (~106 tokens)

Translate for families

Translate counselor-facing output into a family's language, holding the financial aid terms in English on purpose. FAFSA, Pell, SAI, COA and the loan names stay untranslated so a family can match what the school actually sends them against what they were told. Read-only.

Cost: about 173 credits (~$0.173) per call.

Input parameters:

- `sourceText` (string, required): The text to translate. Usually the output of another tool.
- `targetLang` (string, required): Target language code.

### `humanize` (~183 tokens)

Humanize reader-facing text

Rewrite reader-facing prose so it sounds direct, specific, and personal without changing facts or inventing a voice. Use it for outreach, emails, letters, posts, and narrative copy. It preserves quoted text and checks the result against the source. It does not evade or promise to beat AI detectors. Do not use it for code, SQL, JSON, legal text, or technical specifications.

Cost: about 413 credits (~$0.413) per call.

Input parameters:

- `audience` (string): Who will read the text. This changes vocabulary and formality, not the facts.
- `preserveFormatting` (boolean): Keep headings, lists, paragraph breaks, links, and other formatting.
- `strength` (string): light makes surface fixes, standard rewrites AI-sounding sentences, aggressive may rebuild paragraph flow.
- `text` (string, required): The reader-facing prose to edit.

### `account_balance` (~29 tokens)

Check remaining credits

Free. Returns the credits left on this API key. Call it before a long run of billed calls.

### `quote_call` (~88 tokens)

Quote a tool call before paying for it

Free. Validates the input for a tool and returns the exact credit hold a real call would take at your price, plus whether your balance covers it. Use it to budget before a billed call or to lint an input for free.

Input parameters:

- `input` (object): The input you intend to send. Optional; omit for the default estimate.
- `tool` (string, required): Tool name from tools/list.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/the-825-counselorai/api#diagnostics

## Score history

- 2026-09-21: 84
- 2026-09-20: 83
- 2026-09-19: 83
- 2026-09-18: 82
- 2026-09-17: 82
- 2026-09-16: 82
- 2026-09-15: 81
- 2026-09-14: 81
- 2026-09-13: 80
- 2026-09-12: 80
- 2026-09-11: 79
- 2026-09-10: 79
- 2026-09-09: 78
- 2026-09-08: 78
- 2026-09-07: 77
- 2026-09-06: 77
- 2026-09-05: 77
- 2026-09-04: 76
- 2026-09-03: 76
- 2026-09-02: 75

## Common questions

### What is the CounselorAI MCP server?

CounselorAI is an MCP server listed in the public MCP registry as io.github.The-825/counselorai. College-access writing and financial-aid analysis tools for counselors, students, and families. This page covers its hosted endpoint (https://api.counselorai.app/mcp).

### Is the CounselorAI MCP server safe to use?

CounselorAI scores 84 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 CounselorAI MCP server expose?

CounselorAI exposes 13 tools: appeal, rec, letterlens, awardlens, fafsa, and 8 more. Their descriptions and schemas cost roughly 2,430 tokens of context every time the server is loaded.

### Does the CounselorAI MCP server require authentication?

Yes. CounselorAI asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the CounselorAI MCP server still maintained?

CounselorAI is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.counselorai.app/mcp
- Website: https://counselorai.app/
- Changelog RSS feed: https://verifymcp.io/servers/the-825-counselorai/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/the-825-counselorai/api.json
- HTML version of this page: https://verifymcp.io/servers/the-825-counselorai/api